The More, The Better? Active Silencing of Non-Positive Transfer for Efficient Multi-Domain Few-Shot Classification

0Citations
Citations of this article
6Readers
Mendeley users who have this article in their library.

Abstract

Few-shot classification refers to recognizing several novel classes given only a few labeled samples. Many recent methods try to gain an adaptation benefit by learning prior knowledge from more base training domains, aka. multi-domain few-shot classification. However, with extensive empirical evidence, we find more is not always better: current models do not necessarily benefit from pre-training on more base classes and domains, since the pre-trained knowledge might be non-positive for a downstream task. In this work, we hypothesize that such redundant pre-training can be avoided without compromising the downstream performance. Inspired by the selective activating/silencing mechanism in the biological memory system, which enables the brain to learn a new concept from a few experiences both quickly and accurately, we propose to actively silence those redundant base classes and domains for efficient multi-domain few-shot classification. Then, a novel data-driven approach named Active Silencing with hierarchical Subset Selection (AS3) is developed to address two problems: 1) finding a subset of base classes that adequately represent novel classes for efficient positive transfer; and 2) finding a subset of base learners (i.e., domains) with confident accurate prediction in a new domain. Both problems are formulated as distance-based sparse subset selection. We extensively evaluate AS3 on the recent META-DATASET benchmark as well as MNIST, CIFAR10, and CIFAR100, where AS3 achieves over 100% acceleration while maintaining or even improving accuracy. Our code and Appendix are available at https://github.com/indussky8/AS3.

Cite

CITATION STYLE

APA

Zhang, X., Liu, Z., Yang, W., Wang, L., & Zhu, J. (2022). The More, The Better? Active Silencing of Non-Positive Transfer for Efficient Multi-Domain Few-Shot Classification. In MM 2022 - Proceedings of the 30th ACM International Conference on Multimedia (pp. 1993–2001). Association for Computing Machinery, Inc. https://doi.org/10.1145/3503161.3548349

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free