Unsupervised Few-Shot Image Classification
4개 벤치마크 · 논문 28편 · 이 태스크의 논문 보기 →
Benchmarks
Mini-Imagenet 5-way (1-shot)
Mini-Imagenet 5-way (5-shot)
Most implemented
Self-Supervision Can Be a Good Few-Shot Learner
Self-Supervised Prototypical Transfer Learning for Few-Shot Classification
Self-Supervised Learning For Few-Shot Image Classification
BECLR: Batch Enhanced Contrastive Few-Shot Learning
CMVAE: Causal Meta VAE for Unsupervised Meta-Learning
Contrastive Prototypical Network with Wasserstein Confidence Penalty
Papers
BECLR: Batch Enhanced Contrastive Few-Shot Learning
Learning quickly from very few labeled samples is a fundamental attribute that separates machines and humans in the era of deep representation learning. Unsupervised few-shot learning (U-FSL) aspires to bridge this gap b…
Contrastive LearningFew-Shot Image ClassificationFew-Shot LearningRepresentation Learning+2Meta-DM: Applications of Diffusion Models on Few-Shot Learning
In the field of few-shot learning (FSL), extensive research has focused on improving network structures and training strategies. However, the role of data processing modules has not been fully explored. Therefore, in thi…
Few-Shot LearningUnsupervised Few-Shot Image ClassificationCMVAE: Causal Meta VAE for Unsupervised Meta-Learning
Unsupervised meta-learning aims to learn the meta knowledge from unlabeled data and rapidly adapt to novel tasks. However, existing approaches may be misled by the context-bias (e.g. background) from the training data. I…
Few-Shot Image Classificationimage-classificationImage ClassificationMeta-Learning+1Invariant and consistent: Unsupervised representation learning for few-shot visual recognition
Few-shot visual recognition aims to identify novel unseen classes with few labels while learning generalized prior knowledge from base classes. Recent ideas propose to explore this problem in an unsupervised setting, i.e…
Contrastive LearningRepresentation LearningUnsupervised Few-Shot Image ClassificationContrastive Prototypical Network with Wasserstein Confidence Penalty
Unsupervised few-shot learning aims to learn the inductive bias from unlabeled dataset for solving the novel few-shot tasks. The existing unsupervised few-shot learning models and the contrastive learning models follow a…
Contrastive LearningFew-Shot LearningInductive BiasUnsupervised Few-Shot Image Classification+1Unsupervised Few-Shot Image Classification by Learning Features into Clustering Space
Most few-shot image classification methods are trained based on tasks. Usually, tasks are built on base classes with a large number of labeled images, which consumes large effort. Unsupervised few-shot image classificati…
ClassificationClusteringFew-Shot Image Classificationimage-classification+2