Disentangled Feature Representation for Few-Shot Image Classification

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

12 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)10422-10435
Number of pages14
Journal / PublicationIEEE Transactions on Neural Networks and Learning Systems
Volume35
Issue number8
Online published16 Feb 2023
Publication statusPublished - Aug 2024

Abstract

Learning the generalizable feature representation is critical to few-shot image classification. While recent works exploited task-specific feature embedding using meta-tasks for few-shot learning, they are limited in many challenging tasks as being distracted by the excursive features such as the background, domain, and style of the image samples. In this work, we propose a novel disentangled feature representation (DFR) framework, dubbed DFR, for few-shot learning applications. DFR can adaptively decouple the discriminative features that are modeled by the classification branch, from the class-irrelevant component of the variation branch. In general, most of the popular deep few-shot learning methods can be plugged in as the classification branch, thus DFR can boost their performance on various few-shot tasks. Furthermore, we propose a novel FS-DomainNet dataset based on DomainNet, for benchmarking the few-shot domain generalization (DG) tasks. We conducted extensive experiments to evaluate the proposed DFR on general, fine-grained, and cross-domain few-shot classification, as well as few-shot DG, using the corresponding four benchmarks, i.e., mini-ImageNet, tiered-ImageNet, Caltech-UCSD Birds 200-2011 (CUB), and the proposed FS-DomainNet. Thanks to the effective feature disentangling, the DFR-based few-shot classifiers achieved state-of-the-art results on all datasets.

Research Area(s)

  • Task analysis, Feature extraction, Measurement, Learning systems, Training, Visualization, Deep learning, feature disentangling, few-shot classification, image classification

Citation Format(s)

Disentangled Feature Representation for Few-Shot Image Classification. / Cheng, Hao; Wang, Yufei; Li, Haoliang et al.
In: IEEE Transactions on Neural Networks and Learning Systems, Vol. 35, No. 8, 08.2024, p. 10422-10435.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review