LCReg: Long-tailed image classification with Latent Categories based Recognition

Page view(s)
64
Checked on Feb 14, 2024
LCReg: Long-tailed image classification with Latent Categories based Recognition
Title:
LCReg: Long-tailed image classification with Latent Categories based Recognition
Journal Title:
Pattern Recognition
Publication Date:
16 September 2023
Citation:
Liu, W., Wu, Z., Wang, Y., Ding, H., Liu, F., Lin, J., & Lin, G. (2024). LCReg: Long-tailed image classification with Latent Categories based Recognition. Pattern Recognition, 145, 109971. https://doi.org/10.1016/j.patcog.2023.109971
Abstract:
In this work, we tackle the challenging problem of long-tailed image recognition. Previous long-tailed recognition approaches mainly focus on data augmentation or re-balancing strategies for the tail classes to give them more attention during model training. However, these methods are limited by the small number of training images for the tail classes, which results in poor feature representa- tions. To address this issue, we propose the Latent Categories based long-tail Recognition (LCReg) method. Our hypothesis is that common latent features shared by head and tail classes can be used to improve feature representation. Specifically, we learn a set of class-agnostic latent features shared by both head and tail classes, and then use semantic data augmentation on the latent features to implicitly increase the diversity of the training sample. We conduct extensive experiments on five long-tailed image recognition datasets, and the results show that our proposed method significantly improves the baselines.
License type:
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research - AME Programmatic Funds
Grant Reference no. : A20H6b0151

This research / project is supported by the National Research Foundation, Singapore - AI Singapore Programme
Grant Reference no. : AISG-RP-2018-003

This research / project is supported by the Ministry of Education, Singapore - Academic Research Fund Tier 1
Grant Reference no. : RG95/20
Description:
This research is partly supported by the Agency for Science, Technology and Research (A*STAR) under its AME Programmatic Funds (Grant No. A20H6b0151).
ISSN:
0031-3203
Files uploaded:

File Size Format Action
pr-d-22-02969r2-final.pdf 1,008.36 KB PDF Request a copy