Novel Class Discovery
32 papers with code • 3 benchmarks • 3 datasets
The goal of Novel Class Discovery (NCD) is to identify new classes in unlabeled data, by exploiting prior knowledge from known classes. In this specific setup, the data is split in two sets. The first is a labeled set containing known classes and the second is an unlabeled set containing unknown classes that must be discovered.
CIFAR-10
CIFAR-100
SVHN
Most implemented papers
Parametric Classification for Generalized Category Discovery: A Baseline Study
Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples.
Class-relation Knowledge Distillation for Novel Class Discovery
kleinzcy/cr-kd-ncd
•
•
ICCV 2023
In addition, to enable a flexible knowledge distillation scheme for each data point in novel classes, we develop a learnable weighting function for the regularization, which adaptively promotes knowledge transfer based on the semantic similarity between the novel and known classes.
Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images
ClancyZhou/P_Net_Anomaly_Detection
•
•
ECCV 2020
In the end, we further utilize the reconstructed image to extract the structure and measure the difference between structure extracted from original and the reconstructed image.
Meta Discovery: Learning to Discover Novel Classes given Very Limited Data
In this paper, we demystify assumptions behind NCD and find that high-level semantic features should be shared among the seen and unseen classes.
Neighborhood Contrastive Learning for Novel Class Discovery
In this paper, we address Novel Class Discovery (NCD), the task of unveiling new classes in a set of unlabeled samples given a labeled dataset with known classes.
AutoNovel: Automatically Discovering and Learning Novel Visual Categories
k-han/AutoNovel
•
•
We present a new approach called AutoNovel to address this problem by combining three ideas: (1) we suggest that the common approach of bootstrapping an image representation using the labelled data only introduces an unwanted bias, and that this can be avoided by using self-supervised learning to train the representation from scratch on the union of labelled and unlabelled data; (2) we use ranking statistics to transfer the model's knowledge of the labelled classes to the problem of clustering the unlabelled images; and, (3) we train the data representation by optimizing a joint objective function on the labelled and unlabelled subsets of the data, improving both the supervised classification of the labelled data, and the clustering of the unlabelled data.
A Unified Objective for Novel Class Discovery
DonkeyShot21/UNO
•
•
ICCV 2021
In this paper, we study the problem of Novel Class Discovery (NCD).
Novel Class Discovery in Semantic Segmentation
HeliosZhao/NCDSS
•
•
CVPR 2022
We introduce a new setting of Novel Class Discovery in Semantic Segmentation (NCDSS), which aims at segmenting unlabeled images containing new classes given prior knowledge from a labeled set of disjoint classes.
Divide and Conquer: Compositional Experts for Generalized Novel Class Discovery
In response to the explosively-increasing requirement of annotated data, Novel Class Discovery (NCD) has emerged as a promising alternative to automatically recognize unknown classes without any annotation.
Spacing Loss for Discovering Novel Categories
Novel Class Discovery (NCD) is a learning paradigm, where a machine learning model is tasked to semantically group instances from unlabeled data, by utilizing labeled instances from a disjoint set of classes.
