Search Results for author:
Found 144 papers, 81 papers with code
Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization
As recent advances in mobile camera technology have enabled the capability to capture high-resolution images, such as 4K images, the demand for an efficient deblurring model handling large motion has increased.
SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs
While incorporating new information with the retrieval of relevant passages is a promising way to improve QA with LLMs, the existing methods often require additional fine-tuning which becomes infeasible with recent LLMs.
Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
Large language models (LLMs) have shown remarkable performance in various natural language processing tasks.
Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models
To investigate this issue in depth, we introduce the Text-Image Alignment Assessment (TIA2) benchmark, which comprises a diverse collection of text prompts, images, and human annotations.
DreamFlow: High-Quality Text-to-3D Generation by Approximating Probability Flow
Recent progress in text-to-3D generation has been achieved through the utilization of score distillation methods: they make use of the pre-trained text-to-image (T2I) diffusion models by distilling via the diffusion model training objective.
Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
To tackle this issue, we propose content-motion latent diffusion model (CMD), a novel efficient extension of pretrained image diffusion models for video generation.
Improving Diffusion Models for Virtual Try-on
Finally, we present a customization method using a pair of person-garment images, which significantly improves fidelity and authenticity.
Ranked #1 on
Virtual Try-on
on VITON-HD
Online Adaptation of Language Models with a Memory of Amortized Contexts
We propose an amortized feature extraction and memory-augmentation approach to compress and extract information from new documents into compact modulations stored in a memory bank.
Direct Consistency Optimization for Compositional Text-to-Image Personalization
In particular, our method results in a superior Pareto frontier to the baselines.
Querying Easily Flip-flopped Samples for Deep Active Learning
Active learning is a machine learning paradigm that aims to improve the performance of a model by strategically selecting and querying unlabeled data.
NeFL: Nested Federated Learning for Heterogeneous Clients
Previous studies tackle the system heterogeneity by splitting a model into submodels, but with less degree-of-freedom in terms of model architecture.
Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models
Large-scale image generation models, with impressive quality made possible by the vast amount of data available on the Internet, raise social concerns that these models may generate harmful or copyrighted content.
Collaborative Score Distillation for Consistent Visual Synthesis
Generative priors of large-scale text-to-image diffusion models enable a wide range of new generation and editing applications on diverse visual modalities.
Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning
In this paper, we investigate task-specific preferences between pairs of input texts as a new alternative way for such auxiliary data annotation.
infoVerse: A Universal Framework for Dataset Characterization with Multidimensional Meta-information
However, not all samples in these datasets are equally valuable for learning, as some may be redundant or noisy.
S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions
By combining these objectives, S-CLIP significantly enhances the training of CLIP using only a few image-text pairs, as demonstrated in various specialist domains, including remote sensing, fashion, scientific figures, and comics.
IFSeg: Image-free Semantic Segmentation via Vision-Language Model
In this paper, we introduce a novel image-free segmentation task where the goal is to perform semantic segmentation given only a set of the target semantic categories, but without any task-specific images and annotations.
Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck
In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition (i. e., less generalizable), so that one cannot prevent a model from co-adapting on such (so-called) "shortcut" signals: this makes the model fragile in various distribution shifts.
Imitating Graph-Based Planning with Goal-Conditioned Policies
Recently, graph-based planning algorithms have gained much attention to solve goal-conditioned reinforcement learning (RL) tasks: they provide a sequence of subgoals to reach the target-goal, and the agents learn to execute subgoal-conditioned policies.
Guiding Energy-based Models via Contrastive Latent Variables
To enable the joint training of EBM and CRL, we also design a new class of latent-variable EBMs for learning the joint density of data and the contrastive latent variable.
Preference Transformer: Modeling Human Preferences using Transformers for RL
In this paper, we present Preference Transformer, a neural architecture that models human preferences using transformers.
STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables
Learning with few labeled tabular samples is often an essential requirement for industrial machine learning applications as varieties of tabular data suffer from high annotation costs or have difficulties in collecting new samples for novel tasks.
Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning
Unsupervised meta-learning aims to learn generalizable knowledge across a distribution of tasks constructed from unlabeled data.
Video Probabilistic Diffusion Models in Projected Latent Space
Specifically, PVDM is composed of two components: (a) an autoencoder that projects a given video as 2D-shaped latent vectors that factorize the complex cubic structure of video pixels and (b) a diffusion model architecture specialized for our new factorized latent space and the training/sampling procedure to synthesize videos of arbitrary length with a single model.
Multi-View Masked World Models for Visual Robotic Manipulation
In this paper, we investigate how to learn good representations with multi-view data and utilize them for visual robotic manipulation.
Discovering and Mitigating Visual Biases through Keyword Explanation
The keyword explanation form of visual bias offers several advantages, such as a clear group naming for bias discovery and a natural extension for debiasing using these group names.
Modality-Agnostic Variational Compression of Implicit Neural Representations
We introduce a modality-agnostic neural compression algorithm based on a functional view of data and parameterised as an Implicit Neural Representation (INR).
BiasAdv: Bias-Adversarial Augmentation for Model Debiasing
Our key idea is that an adversarial attack on a biased model that makes decisions based on spurious correlations may generate synthetic bias-conflicting samples, which can then be used as augmented training data for learning a debiased model.
Confidence-aware Training of Smoothed Classifiers for Certified Robustness
Under the smoothed classifiers, the fundamental trade-off between accuracy and (adversarial) robustness has been well evidenced in the literature: i. e., increasing the robustness of a classifier for an input can be at the expense of decreased accuracy for some other inputs.
OAMixer: Object-aware Mixing Layer for Vision Transformers
Using the object labels, OAMixer computes a reweighting mask with a learnable scale parameter that intensifies the interaction of patches containing similar objects and applies the mask to the patch mixing layers.
Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling
(a) Fairness Intervention (FI): emphasize the minority samples that are hard to generate due to the spurious correlation in the training dataset.
Scalable Neural Video Representations with Learnable Positional Features
Succinct representation of complex signals using coordinate-based neural representations (CNRs) has seen great progress, and several recent efforts focus on extending them for handling videos.
Meta-Learning with Self-Improving Momentum Target
The idea of using a separately trained target model (or teacher) to improve the performance of the student model has been increasingly popular in various machine learning domains, and meta-learning is no exception; a recent discovery shows that utilizing task-wise target models can significantly boost the generalization performance.
String-based Molecule Generation via Multi-decoder VAE
In this paper, we investigate the problem of string-based molecular generation via variational autoencoders (VAEs) that have served a popular generative approach for various tasks in artificial intelligence.
RenyiCL: Contrastive Representation Learning with Skew Renyi Divergence
Here, the choice of data augmentation is sensitive to the quality of learned representations: as harder the data augmentations are applied, the views share more task-relevant information, but also task-irrelevant one that can hinder the generalization capability of representation.
NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation
Test-time adaptation (TTA) is an emerging paradigm that addresses distributional shifts between training and testing phases without additional data acquisition or labeling cost; only unlabeled test data streams are used for continual model adaptation.
Time Is MattEr: Temporal Self-supervision for Video Transformers
Understanding temporal dynamics of video is an essential aspect of learning better video representations.
TSPipe: Learn from Teacher Faster with Pipelines
The teacher-student (TS) framework, training a (student) network by utilizing an auxiliary superior (teacher) network, has been adopted as a popular training paradigm in many machine learning schemes, since the seminal work---Knowledge distillation (KD) for model compression and transfer learning.
Patch-level Representation Learning for Self-supervised Vision Transformers
Despite its simplicity, we demonstrate that it can significantly improve the performance of existing SSL methods for various visual tasks, including object detection and semantic segmentation.
Zero-shot Blind Image Denoising via Implicit Neural Representations
Recent denoising algorithms based on the "blind-spot" strategy show impressive blind image denoising performances, without utilizing any external dataset.
Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation
The paradigm of worst-group loss minimization has shown its promise in avoiding to learn spurious correlations, but requires costly additional supervision on spurious attributes.
SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning
In order to leverage unlabeled samples for reward learning, we infer pseudo-labels of the unlabeled samples based on the confidence of the preference predictor.
Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks
In this paper, we found that the recent emerging paradigm of implicit neural representations (INRs) that encodes a continuous signal into a parameterized neural network effectively mitigates the issue.
Ranked #25 on
Video Generation
on UCF-101
Self-Supervised Dense Consistency Regularization for Image-to-Image Translation
Unsupervised image-to-image translation has gained considerable attention due to the recent impressive progress based on generative adversarial networks (GANs).
Contrastive Dual Gating: Learning Sparse Features With Contrastive Learning
Contrastive learning (or its variants) has recently become a promising direction in the self-supervised learning domain, achieving similar performance as supervised learning with minimum fine-tuning.
Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing
However, they now suffer from lack of sample diversification as they always deterministically select regions with maximum saliency, injecting bias into the augmented data.
DAPPER: Label-Free Performance Estimation after Personalization for Heterogeneous Mobile Sensing
However, various factors such as different users, devices, and environments impact the performance of such applications, thus making the domain shift (i. e., distributional shift between the training domain and the target domain) a critical issue in mobile sensing.
Improving Transferability of Representations via Augmentation-Aware Self-Supervision
Recent unsupervised representation learning methods have shown to be effective in a range of vision tasks by learning representations invariant to data augmentations such as random cropping and color jittering.
SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness
Randomized smoothing is currently a state-of-the-art method to construct a certifiably robust classifier from neural networks against $\ell_2$-adversarial perturbations.
Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning
Behavioral cloning has proven to be effective for learning sequential decision-making policies from expert demonstrations.
RoMA: Robust Model Adaptation for Offline Model-based Optimization
We consider the problem of searching an input maximizing a black-box objective function given a static dataset of input-output queries.
Meta-Learning Sparse Implicit Neural Representations
Implicit neural representations are a promising new avenue of representing general signals by learning a continuous function that, parameterized as a neural network, maps the domain of a signal to its codomain; the mapping from spatial coordinates of an image to its pixel values, for example.
Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning
In this paper, we present HIerarchical reinforcement learning Guided by Landmarks (HIGL), a novel framework for training a high-level policy with a reduced action space guided by landmarks, i. e., promising states to explore.
Efficient Exploration
Hierarchical Reinforcement Learning
+2
PASS: Patch-Aware Self-Supervision for Vision Transformer
This paper aims to improve their performance further by utilizing the architectural advantages of the underlying neural network, as the current state-of-the-art visual pretext tasks for self-supervised learning do not enjoy the benefit, i. e., they are architecture-agnostic.
What Makes Better Augmentation Strategies? Augment Difficult but Not too Different
Remarkably, our method is more effective on the challenging low-data and class-imbalanced regimes, and the learned augmentation policy is well-transferable to the different tasks and models.
Model-augmented Prioritized Experience Replay
Experience replay is an essential component in off-policy model-free reinforcement learning (MfRL).
Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning
Although these two sources are both important factors for learning robust policies of agents, prior works do not separate them or deal with only a single risk source, which could lead to suboptimal equilibria.
Ranked #1 on
SMAC+
on Off_Near_parallel
Multi-agent Reinforcement Learning
reinforcement-learning
+3
Object-aware Contrastive Learning for Debiased Scene Representation
Contrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentations.
Abstract Reasoning via Logic-guided Generation
Abstract reasoning, i. e., inferring complicated patterns from given observations, is a central building block of artificial general intelligence.
Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble
Recent advance in deep offline reinforcement learning (RL) has made it possible to train strong robotic agents from offline datasets.
OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Data
Semi-supervised learning (SSL) has been a powerful strategy to incorporate few labels in learning better representations.
Co$^2$L: Contrastive Continual Learning
Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks than joint-training methods relying on task-specific supervision.
Quality-Agnostic Image Recognition via Invertible Decoder
Our two-stage scheme allows the network to produce clean-like and robust features from any quality images, by reconstructing their clean images via the invertible decoder.
Ranked #17 on
Domain Generalization
on ImageNet-C
SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Adversarial Robustness
Randomized smoothing is currently a state-of-the-art method to construct a certifiably robust classifier from neural networks against $\ell_2$-adversarial perturbations.
Entropy Weighted Adversarial Training
Adversarial training methods, which minimizes the loss of adversarially-perturbed training examples, have been extensively studied as a solution to improve the robustness of the deep neural networks.
Scaling Neural Tangent Kernels via Sketching and Random Features
To accelerate learning with NTK, we design a near input-sparsity time approximation algorithm for NTK, by sketching the polynomial expansions of arc-cosine kernels: our sketch for the convolutional counterpart of NTK (CNTK) can transform any image using a linear runtime in the number of pixels.
Self-Improved Retrosynthetic Planning
Our main idea is based on a self-improving procedure that trains the model to imitate successful trajectories found by itself.
Ranked #4 on
Multi-step retrosynthesis
on USPTO-190
RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning
Retrosynthesis, of which the goal is to find a set of reactants for synthesizing a target product, is an emerging research area of deep learning.
Consistency and Monotonicity Regularization for Neural Knowledge Tracing
Knowledge Tracing (KT), tracking a human's knowledge acquisition, is a central component in online learning and AI in Education.
Random Features for the Neural Tangent Kernel
We combine random features of the arc-cosine kernels with a sketching-based algorithm which can run in linear with respect to both the number of data points and input dimension.
Training GANs with Stronger Augmentations via Contrastive Discriminator
Recent works in Generative Adversarial Networks (GANs) are actively revisiting various data augmentation techniques as an effective way to prevent discriminator overfitting.
Consistency Regularization for Adversarial Robustness
Adversarial training (AT) is currently one of the most successful methods to obtain the adversarial robustness of deep neural networks.
State Entropy Maximization with Random Encoders for Efficient Exploration
Recent exploration methods have proven to be a recipe for improving sample-efficiency in deep reinforcement learning (RL).
Model-Augmented Q-learning
We show that the proposed scheme, called Model-augmented $Q$-learning (MQL), obtains a policy-invariant solution which is identical to the solution obtained by learning with true reward.
Addressing Distribution Shift in Online Reinforcement Learning with Offline Datasets
As it turns out, fine-tuning offline RL agents is a non-trivial challenge, due to distribution shift – the agent encounters out-of-distribution samples during online interaction, which may cause bootstrapping error in Q-learning and instability during fine-tuning.
Co2L: Contrastive Continual Learning
Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks than cross-entropy based methods which rely on task-specific supervision.
MASKER: Masked Keyword Regularization for Reliable Text Classification
We claim that one central obstacle to the reliability is the over-reliance of the model on a limited number of keywords, instead of looking at the whole context.
Learning from Failure: De-biasing Classifier from Biased Classifier
Neural networks often learn to make predictions that overly rely on spurious corre- lation existing in the dataset, which causes the model to be biased.
DiscFace: Minimum Discrepancy Learning for Deep Face Recognition
Softmax-based learning methods have shown state-of-the-art performances on large-scale face recognition tasks.
Ranked #1 on
Face Verification
on CALFW
Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning
Model-based reinforcement learning (RL) has shown great potential in various control tasks in terms of both sample-efficiency and final performance.
Provable Memorization via Deep Neural Networks using Sub-linear Parameters
It is known that $O(N)$ parameters are sufficient for neural networks to memorize arbitrary $N$ input-label pairs.
i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning
Contrastive representation learning has shown to be effective to learn representations from unlabeled data.
Layer-adaptive sparsity for the Magnitude-based Pruning
Recent discoveries on neural network pruning reveal that, with a carefully chosen layerwise sparsity, a simple magnitude-based pruning achieves state-of-the-art tradeoff between sparsity and performance.
Few-shot Visual Reasoning with Meta-analogical Contrastive Learning
While humans can solve a visual puzzle that requires logical reasoning by observing only few samples, it would require training over large amount of data for state-of-the-art deep reasoning models to obtain similar performance on the same task.
Time-Reversal Symmetric ODE Network
Time-reversal symmetry, which requires that the dynamics of a system should not change with the reversal of time axis, is a fundamental property that frequently holds in classical and quantum mechanics.
Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning
While semi-supervised learning (SSL) has proven to be a promising way for leveraging unlabeled data when labeled data is scarce, the existing SSL algorithms typically assume that training class distributions are balanced.
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
Based on this, we propose a new detection score that is specific to the proposed training scheme.
Learning to Sample with Local and Global Contexts in Experience Replay Buffer
Experience replay, which enables the agents to remember and reuse experience from the past, has played a significant role in the success of off-policy reinforcement learning (RL).
Learning from Failure: Training Debiased Classifier from Biased Classifier
Neural networks often learn to make predictions that overly rely on spurious correlation existing in the dataset, which causes the model to be biased.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
Guiding Deep Molecular Optimization with Genetic Exploration
De novo molecular design attempts to search over the chemical space for molecules with the desired property.
QTRAN++: Improved Value Transformation for Cooperative Multi-Agent Reinforcement Learning
QTRAN is a multi-agent reinforcement learning (MARL) algorithm capable of learning the largest class of joint-action value functions up to date.
Learning to Generate Noise for Multi-Attack Robustness
Adversarial learning has emerged as one of the successful techniques to circumvent the susceptibility of existing methods against adversarial perturbations.
Learning What to Defer for Maximum Independent Sets
Designing efficient algorithms for combinatorial optimization appears ubiquitously in various scientific fields.
Minimum Width for Universal Approximation
In this work, we provide the first definitive result in this direction for networks using the ReLU activation functions: The minimum width required for the universal approximation of the $L^p$ functions is exactly $\max\{d_x+1, d_y\}$.
Learning Bounds for Risk-sensitive Learning
The second result, based on a novel variance-based characterization of OCE, gives an expected loss guarantee with a suppressed dependence on the smoothness of the selected OCE.
Consistency Regularization for Certified Robustness of Smoothed Classifiers
A recent technique of randomized smoothing has shown that the worst-case (adversarial) $\ell_2$-robustness can be transformed into the average-case Gaussian-robustness by "smoothing" a classifier, i. e., by considering the averaged prediction over Gaussian noise.
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning
Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics.
Model-based Reinforcement Learning
reinforcement-learning
+1
M2m: Imbalanced Classification via Major-to-minor Translation
In most real-world scenarios, labeled training datasets are highly class-imbalanced, where deep neural networks suffer from generalizing to a balanced testing criterion.
Ranked #43 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
Regularizing Class-wise Predictions via Self-knowledge Distillation
Deep neural networks with millions of parameters may suffer from poor generalization due to overfitting.
Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs
Generative adversarial networks (GANs) have shown outstanding performance on a wide range of problems in computer vision, graphics, and machine learning, but often require numerous training data and heavy computational resources.
Ranked #5 on
10-shot image generation
on Babies
Lookahead: a Far-Sighted Alternative of Magnitude-based Pruning
Magnitude-based pruning is one of the simplest methods for pruning neural networks.
Mining GOLD Samples for Conditional GANs
Conditional generative adversarial networks (cGANs) have gained a considerable attention in recent years due to its class-wise controllability and superior quality for complex generation tasks.
Self-supervised Label Augmentation via Input Transformations
Our main idea is to learn a single unified task with respect to the joint distribution of the original and self-supervised labels, i. e., we augment original labels via self-supervision of input transformation.
Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning
Deep reinforcement learning (RL) agents often fail to generalize to unseen environments (yet semantically similar to trained agents), particularly when they are trained on high-dimensional state spaces, such as images.
Deep Auto-Deferring Policy for Combinatorial Optimization
Designing efficient algorithms for combinatorial optimization appears ubiquitously in various scientific fields.
Adversarial Neural Pruning with Latent Vulnerability Suppression
Despite the remarkable performance of deep neural networks on various computer vision tasks, they are known to be susceptible to adversarial perturbations, which makes it challenging to deploy them in real-world safety-critical applications.
Polynomial Tensor Sketch for Element-wise Function of Low-Rank Matrix
This paper studies how to sketch element-wise functions of low-rank matrices.
Learning What and Where to Transfer
To address the issue, we propose a novel transfer learning approach based on meta-learning that can automatically learn what knowledge to transfer from the source network to where in the target network.
Spectral Approximate Inference
Our contribution is two-fold: (a) we first propose a fully polynomial-time approximation scheme (FPTAS) for approximating the partition function of GM associating with a low-rank coupling matrix; (b) for general high-rank GMs, we design a spectral mean-field scheme utilizing (a) as a subroutine, where it approximates a high-rank GM into a product of rank-1 GMs for an efficient approximation of the partition function.
Training CNNs with Selective Allocation of Channels
Recent progress in deep convolutional neural networks (CNNs) have enabled a simple paradigm of architecture design: larger models typically achieve better accuracy.
Selective Convolutional Units: Improving CNNs via Channel Selectivity
Bottleneck structures with identity (e. g., residual) connection are now emerging popular paradigms for designing deep convolutional neural networks (CNN), for processing large-scale features efficiently.
Robust Determinantal Generative Classifier for Noisy Labels and Adversarial Attacks
For instance, on CIFAR-10 dataset containing 45% noisy training labels, we improve the test accuracy of a deep model optimized by the state-of-the-art noise-handling training method from33. 34% to 43. 02%.
Instance-aware Image-to-Image Translation
Unsupervised image-to-image translation has gained considerable attention due to the recent impressive progress based on generative adversarial networks (GANs).
Overcoming Catastrophic Forgetting with Unlabeled Data in the Wild
Lifelong learning with deep neural networks is well-known to suffer from catastrophic forgetting: the performance on previous tasks drastically degrades when learning a new task.
Robust Inference via Generative Classifiers for Handling Noisy Labels
Large-scale datasets may contain significant proportions of noisy (incorrect) class labels, and it is well-known that modern deep neural networks (DNNs) poorly generalize from such noisy training datasets.
InstaGAN: Instance-aware Image-to-Image Translation
Our comparative evaluation demonstrates the effectiveness of the proposed method on different image datasets, in particular, in the aforementioned challenging cases.
Learning to Specialize with Knowledge Distillation for Visual Question Answering
The proposed framework is model-agnostic and applicable to any tasks other than VQA, e. g., image classification with a large number of labels but few per-class examples, which is known to be difficult under existing MCL schemes.
A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
Detecting test samples drawn sufficiently far away from the training distribution statistically or adversarially is a fundamental requirement for deploying a good classifier in many real-world machine learning applications.
Ranked #2 on
Out-of-Distribution Detection
on MS-1M vs. IJB-C
Anytime Neural Prediction via Slicing Networks Vertically
This is remarkable due to their simplicity and effectiveness, but training many thin sub-networks jointly faces a new challenge on training complexity.
Hierarchical Novelty Detection for Visual Object Recognition
The essential ingredients of our methods are confidence-calibrated classifiers, data relabeling, and the leave-one-out strategy for modeling novel classes under the hierarchical taxonomy.
Bucket Renormalization for Approximate Inference
Probabilistic graphical models are a key tool in machine learning applications.
Stochastic Chebyshev Gradient Descent for Spectral Optimization
A large class of machine learning techniques requires the solution of optimization problems involving spectral functions of parametric matrices, e. g. log-determinant and nuclear norm.
Gauged Mini-Bucket Elimination for Approximate Inference
Recently, so-called gauge transformations were used to improve variational lower bounds on $Z$.
Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples
The problem of detecting whether a test sample is from in-distribution (i. e., training distribution by a classifier) or out-of-distribution sufficiently different from it arises in many real-world machine learning applications.
Confident Multiple Choice Learning
Ensemble methods are arguably the most trustworthy techniques for boosting the performance of machine learning models.
Simplified Stochastic Feedforward Neural Networks
In this paper, we aim at developing efficient training methods for SFNN, in particular using known architectures and pre-trained parameters of DNN.
Rapid Mixing Swendsen-Wang Sampler for Stochastic Partitioned Attractive Models
The Gibbs sampler is a particularly popular Markov chain used for learning and inference problems in Graphical Models (GMs).
Sequential Local Learning for Latent Graphical Models
Learning parameters of latent graphical models (GM) is inherently much harder than that of no-latent ones since the latent variables make the corresponding log-likelihood non-concave.
Faster Greedy MAP Inference for Determinantal Point Processes
Determinantal point processes (DPPs) are popular probabilistic models that arise in many machine learning tasks, where distributions of diverse sets are characterized by matrix determinants.
Gauging Variational Inference
Computing partition function is the most important statistical inference task arising in applications of Graphical Models (GM).
Contextual Linear Bandits under Noisy Features: Towards Bayesian Oracles
This implies that classical approaches cannot guarantee a non-trivial regret bound.
Iterative Bayesian Learning for Crowdsourced Regression
Crowdsourcing platforms emerged as popular venues for purchasing human intelligence at low cost for large volume of tasks.
Synthesis of MCMC and Belief Propagation
In this paper, we introduce MCMC algorithms correcting the approximation error of BP, i. e., we provide a way to compensate for BP errors via a consecutive BP-aware MCMC.
Approximating the Spectral Sums of Large-scale Matrices using Chebyshev Approximations
Computation of the trace of a matrix function plays an important role in many scientific computing applications, including applications in machine learning, computational physics (e. g., lattice quantum chromodynamics), network analysis and computational biology (e. g., protein folding), just to name a few application areas.
Data Structures and Algorithms
MCMC assisted by Belief Propagation
Furthermore, we also design an efficient rejection-free MCMC scheme for approximating the full series.
Adiabatic Persistent Contrastive Divergence Learning
This paper studies the problem of parameter learning in probabilistic graphical models having latent variables, where the standard approach is the expectation maximization algorithm alternating expectation (E) and maximization (M) steps.
Optimal Inference in Crowdsourced Classification via Belief Propagation
Crowdsourcing systems are popular for solving large-scale labelling tasks with low-paid workers.
Minimum Weight Perfect Matching via Blossom Belief Propagation
Max-product Belief Propagation (BP) is a popular message-passing algorithm for computing a Maximum-A-Posteriori (MAP) assignment over a distribution represented by a Graphical Model (GM).
Large-scale Log-determinant Computation through Stochastic Chebyshev Expansions
Logarithms of determinants of large positive definite matrices appear ubiquitously in machine learning applications including Gaussian graphical and Gaussian process models, partition functions of discrete graphical models, minimum-volume ellipsoids, metric learning and kernel learning.
Scalable Iterative Algorithm for Robust Subspace Clustering
Subspace clustering (SC) is a popular method for dimensionality reduction of high-dimensional data, where it generalizes Principal Component Analysis (PCA).
Max-Product Belief Propagation for Linear Programming: Applications to Combinatorial Optimization
The max-product {belief propagation} (BP) is a popular message-passing heuristic for approximating a maximum-a-posteriori (MAP) assignment in a joint distribution represented by a graphical model (GM).
A Graphical Transformation for Belief Propagation: Maximum Weight Matchings and Odd-Sized Cycles
It was recently shown that BP converges to the correct MAP assignment for a class of loopy GMs with the following common feature: the Linear Programming (LP) relaxation to the MAP problem is tight (has no integrality gap).
Loop Calculus and Bootstrap-Belief Propagation for Perfect Matchings on Arbitrary Graphs
This manuscript discusses computation of the Partition Function (PF) and the Minimum Weight Perfect Matching (MWPM) on arbitrary, non-bipartite graphs.
Belief Propagation for Linear Programming
For this class of problems, MAP inference can be stated as an integer LP with an LP relaxation that coincides with minimization of the BFE at ``zero temperature".
