Revisiting Local Descriptor for Improved Few-Shot Classification Article Swipe

MAKE IMPACT

Jun He , Richang Hong , Xueliang Liu , Mingliang Xu , Qianru Sun · YOU? · · 2021 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2103.16009

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 \textbf{DCAP} for few-shot classification, in which we investigate how one can improve the quality of embeddings by leveraging \textbf{D}ense \textbf{C}lassification and \textbf{A}ttentive \textbf{P}ooling. 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 a bunch 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 (GAP) 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. Code is available at: \url{https://github.com/Ukeyboard/dcap/}.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2103.16009

PDF

https://arxiv.org/pdf/2103.16009

OA Status

green

Related Works

10

OpenAlex ID

https://openalex.org/W4291172217

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4291172217

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2103.16009

Digital Object Identifier

Title

Revisiting Local Descriptor for Improved Few-Shot Classification

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2021

Year of publication

Publication date

2021-03-30

Full publication date if available

Authors

Jun He, Richang Hong, Xueliang Liu, Mingliang Xu, Qianru Sun

List of authors in order

Landing page

https://arxiv.org/abs/2103.16009

Publisher landing page

PDF URL

https://arxiv.org/pdf/2103.16009

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2103.16009

Direct OA link when available

Concepts

Pooling, Computer science, Classifier (UML), Artificial intelligence, Shot (pellet), Benchmark (surveying), Feature (linguistics), Machine learning, Pattern recognition (psychology), Context (archaeology), Data mining, Geodesy, Philosophy, Chemistry, Geography, Linguistics, Biology, Organic chemistry, Paleontology

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload