Publication Type

Journal Article

Version

acceptedVersion

Publication Date

6-2022

Abstract

Few-shot classification studies the problem of quickly adapting a deep learner to understanding novel classes based on few support images. In this context, recent research efforts have been aimed at designing more and more complex classifiers that measure similarities between query and support images but left the importance of feature embeddings seldom explored. We show that the reliance on sophisticated classifiers is not necessary, and a simple classifier applied directly to improved feature embeddings can instead outperform most of the leading methods in the literature. To this end, we present a new method, named DCAP, for few-shot classification, in which we investigate how one can improve the quality of embeddings by leveraging Dense Classification and Attentive Pooling (DCAP). Specifically, we propose to train a learner on base classes with abundant samples to solve dense classification problem first and then meta-train the learner on plenty of randomly sampled few-shot tasks to adapt it to few-shot scenario or the test time scenario. During meta-training, we suggest to pool feature maps by applying attentive pooling instead of the widely used global average pooling to prepare embeddings for few-shot classification. Attentive pooling learns to reweight local descriptors, explaining what the learner is looking for as evidence for decision making. Experiments on two benchmark datasets show the proposed method to be superior in multiple few-shot settings while being simpler and more explainable.

Keywords

few-shot learning, image classification, visual recognition, meta-learning, attention networks

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering

Publication

ACM Transactions on Multimedia Computing, Communications and Applications

Volume

18

Issue

2s

First Page

1

Last Page

23

ISSN

1551-6857

Identifier

10.1145/3511917

Publisher

Association for Computing Machinery (ACM)

Additional URL

https://doi.org/10.1145/3511917

Share

COinS