Spatial Contrastive Learning for Few-Shot Classification

Autor:	Ouali, Yassine, Hudelot, Céline, Tami, Myriam
Rok vydání:	2020
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	In this paper, we explore contrastive learning for few-shot classification, in which we propose to use it as an additional auxiliary training objective acting as a data-dependent regularizer to promote more general and transferable features. In particular, we present a novel attention-based spatial contrastive objective to learn locally discriminative and class-agnostic features. As a result, our approach overcomes some of the limitations of the cross-entropy loss, such as its excessive discrimination towards seen classes, which reduces the transferability of features to unseen classes. With extensive experiments, we show that the proposed method outperforms state-of-the-art approaches, confirming the importance of learning good and transferable embeddings for few-shot learning. Comment: ECML/PKDD 2021
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2012.13831 Zobrazit plný text záznamu View this record from Arxiv