Trainable Class Prototypes for Few-Shot Learning
Metric learning is a widely used method for few shot learning in which the quality of prototypes plays a key role in the algorithm. In this paper we propose the trainable prototypes for distance measure instead of the artificial ones within the meta-training and task-training framework. Also to avoid the disadvantages that the episodic meta-training brought, we adopt non-episodic meta-training based on self-supervised learning. Overall we solve the few-shot tasks in two phases: meta-training a transferable feature extractor via self-supervised learning and training the prototypes for metric classification. In addition, the simple attention mechanism is used in both meta-training and task-training. Our method achieves state-of-the-art performance in a variety of established few-shot tasks on the standard few-shot visual classification dataset, with about 20% increase compared to the available unsupervised few-shot learning methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Few-Shot LearningMetric LearningSelf-Supervised LearningUnsupervised Few-Shot Image ClassificationUnsupervised Few-Shot LearningSimilar Papers 제목 키워드 기반
EfficientFSL: Enhancing Few-Shot Classification via Query-Only Tuning in Vision Transformers
Large models such as Vision Transformers (ViTs) have demonstrated remarkable superiority over smaller architectures like ResNet in few-shot classification, owing to their powerful representational capacity. However, fine…
Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning
We propose a novel framework for few-shot learning by leveraging large-scale vision-language models such as CLIP. Motivated by unimodal prototypical networks for few-shot learning, we introduce Proto-CLIP which utilizes …
Few-Shot Image ClassificationFew-Shot LearningFedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning
Recently, Heterogeneous Federated Learning (HtFL) has attracted attention due to its ability to support heterogeneous models and data. To reduce the high communication cost of transmitting model parameters, a major chall…
Contrastive LearningFederated LearningDual-Distilled Heterogeneous Federated Learning with Adaptive Margins for Trainable Global Prototypes
Heterogeneous Federated Learning (HFL) has gained significant attention for its capacity to handle both model and data heterogeneity across clients. Prototype-based HFL methods emerge as a promising solution to address s…
Knowledge DistillationContrastive LearningFederated LearningFew-shot Learning with Big Prototypes
Using dense vectors, i.e., prototypes, to represent abstract information of classes has become a common approach in low-data machine learning scenarios. Typically, prototypes are mean output embeddings over the instances…
Few-Shot Learning