Do We Need Neural Collapse? Learning Diverse Features for Fine-grained and Long-tail ClassificationDownload PDF

Published: 01 Feb 2023, Last Modified: 13 Feb 2023Submitted to ICLR 2023Readers: Everyone
Keywords: Neural Collapse, Diverse deep learning features, Finegrained transfer learning
TL;DR: Neural collapse is not what you need: Deep features with within-class diversity improve the performance of fine-grained and long-tail learning
Abstract: Feature extractors learned from supervised training of deep neural networks have demonstrated superior performance over handcrafted ones. Recently, it is shown that such learned features have a neural collapse property, where within-class features collapse to the class mean and different class means are maximally separated. This paper examines the neural collapse property in the context of fine-grained classification tasks, where a feature extractor pretrained from a classification task with coarse labels is used for generating features for a downstream classification task with fine-grained labels. We argue that the within-class feature collapse is an undesirable property for fine-grained classification. Hence, we introduce a geometric arrangement of features called the maximal-separating-cone, where within-class features lie in a cone of nontrivial radius instead of collapsing to the class mean, and cones of different classes are maximally separated. We present a technique based on classifier weight and training loss design to produce such an arrangement. Experimentally we demonstrate an improved fine-grained classification performance with a feature extractor pretrained by our method. Moreover, our technique also provides benefits for the classification on data with long-tail distribution over classes. Our work may motivate future efforts on the design of better geometric arrangements of deep features.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning
16 Replies