Cross-Domain Few-Shot
55 papers with code • 9 benchmarks • 6 datasets
Benchmarks
These leaderboards are used to track progress in Cross-Domain Few-Shot
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Cross-Domain Few-Shot models and implementations
CUB-200-2011
mini-Imagenet
Places
Places205
EuroSAT
Earth on Canvas
Most implemented papers
Few-Shot Learning with Graph Neural Networks
We propose to study the problem of few-shot learning with the prism of inference on a partially observed graphical model, constructed from a collection of input images whose label can be either observed or not.
Cross-domain Few-shot Learning with Task-specific Adapters
google-research/meta-dataset
•
•
CVPR 2022
In this paper, we look at the problem of cross-domain few-shot classification that aims to learn a classifier from previously unseen classes and domains with few labeled samples.
Self-Supervised Learning For Few-Shot Image Classification
In this paper, we proposed to train a more generalized embedding network with self-supervised learning (SSL) which can provide robust representation for downstream tasks by learning from the data itself.
A Broader Study of Cross-Domain Few-Shot Learning
IBM/cdfsl-benchmark
•
•
ECCV 2020
Extensive experiments on the proposed benchmark are performed to evaluate state-of-art meta-learning approaches, transfer learning approaches, and newer methods for cross-domain few-shot learning.
Cross-Domain Few-Shot Learning by Representation Fusion
ml-jku/chef
•
•
On the few-shot datasets miniImagenet and tieredImagenet with small domain shifts, CHEF is competitive with state-of-the-art methods.
Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition
open-debin/bayesian_mqda
•
•
ICCV 2021
Current state-of-the-art few-shot learners focus on developing effective training procedures for feature representations, before using simple, e. g. nearest centroid, classifiers.
On Label-Efficient Computer Vision: Building Fast and Effective Few-Shot Image Classifiers
plai-group/simple-cnaps
•
•
University of British Columbia Theses and Dissertations 2021
The first method, Simple CNAPS, employs a hierarchically regularized Mahalanobis-distance based classifier combined with a state of the art neural adaptive feature extractor to achieve strong performance on Meta-Dataset, mini-ImageNet and tiered-ImageNet benchmarks.
Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning
The first method, Simple CNAPS, employs a hierarchically regularized Mahalanobis-distance based classifier combined with a state of the art neural adaptive feature extractor to achieve strong performance on Meta-Dataset, mini-ImageNet and tiered-ImageNet benchmarks.
Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty
sungnyun/understanding-cdfsl
•
•
This data enables self-supervised pre-training on the target domain, in addition to supervised pre-training on the source domain.
Universal Representations: A Unified Look at Multiple Task and Domain Learning
vico-uoe/universalrepresentations
•
•
We propose a unified look at jointly learning multiple vision tasks and visual domains through universal representations, a single deep neural network.
