Unsupervised Few-Shot Image Classification

15 papers with code • 4 benchmarks • 2 datasets

In contrast to (supervised) few-shot image classification, only the unlabeled dataset is available in the pre-training or meta-training stage for unsupervised few-shot image classification.

Libraries

Use these libraries to find Unsupervised Few-Shot Image Classification models and implementations

Most implemented papers

Self-Supervision Can Be a Good Few-Shot Learner

bbbdylan/unisiam 19 Jul 2022

Specifically, we maximize the mutual information (MI) of instances and their representations with a low-bias MI estimator to perform self-supervised pre-training.

Self-Supervised Learning For Few-Shot Image Classification

Alibaba-AAIG/SSL-FEW-SHOT 14 Nov 2019

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.

Self-Supervised Prototypical Transfer Learning for Few-Shot Classification

indy-lab/ProtoTransfer 19 Jun 2020

Building on these insights and on advances in self-supervised learning, we propose a transfer learning approach which constructs a metric embedding that clusters unlabeled prototypical samples and their augmentations closely together.

Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning

ojss/samptransfer CVPR 2021

The majority of existing few-shot learning methods describe image relations with binary labels.

Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation

WonderSeven/ULDA 13 Apr 2020

Importantly, we highlight the value and importance of the distribution diversity in the augmentation-based pretext few-shot tasks, which can effectively alleviate the overfitting problem and make the few-shot model learn more robust feature representations.

Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks

hanlu-nju/revisiting-uml 30 Nov 2020

Meta-learning has become a practical approach towards few-shot image classification, where "a strategy to learn a classifier" is meta-learned on labeled base classes and can be applied to tasks with novel classes.

Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-Learning

db-Lee/Meta-GMVAE ICLR 2021

Then, the learned model can be used for downstream few-shot classification tasks, where we obtain task-specific parameters by performing semi-supervised EM on the latent representations of the support and query set, and predict labels of the query set by computing aggregated posteriors.

Multi-level Second-order Few-shot Learning

hongguangzhang/mlso-tmm-master 15 Jan 2022

The goal of multi-level feature design is to extract feature representations at different layer-wise levels of CNN, realizing several levels of visual abstraction to achieve robust few-shot learning.

Self-Supervised Class-Cognizant Few-Shot Classification

ojss/c3lr 15 Feb 2022

Unsupervised learning is argued to be the dark matter of human intelligence.

Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning

xingpingdong/pl-cfe 27 Sep 2022

In this work, we prove that the core reason for this is lack of a clustering-friendly property in the embedding space.