Abstract
Deep neural networks frequently suffer from performance degradation when the training data is long-tailed because several majority classes dominate the training, resulting in a biased model. Recent studies have made a great effort in solving this issue by obtaining good representations from data space, but few of them pay attention to the influence of feature norm on the predicted results. In this paper, we therefore address the long-tailed problem from feature space and thereby propose the feature-balanced loss. Specifically, we encourage larger feature norms of tail classes by giving them relatively stronger stimuli. Moreover, the stimuli intensity is gradually increased in the way of curriculum learning, which improves the generalization of the tail classes, meanwhile maintaining the performance of the head classes. Extensive experiments on multiple popular long-tailed recognition benchmarks demonstrate that the feature-balanced loss achieves superior performance gains compared with the state-of-the-art methods.
Original language | English |
---|---|
Title of host publication | 2022 IEEE International Conference on Multimedia and Expo (ICME) |
Publisher | IEEE |
Number of pages | 6 |
ISBN (Electronic) | 9781665485630 |
ISBN (Print) | 9781665485647 |
DOIs | |
Publication status | Published - 18 Jul 2022 |
Event | 2022 IEEE International Conference on Multimedia and Expo, ICME 2022 - Taipei, Taiwan Duration: 18 Jul 2022 → 22 Jul 2022 https://ieeexplore.ieee.org/xpl/conhome/9859562/proceeding |
Publication series
Name | IEEE International Conference on Multimedia and Expo (ICME) |
---|---|
ISSN (Print) | 1945-7871 |
ISSN (Electronic) | 1945-788X |
Conference
Conference | 2022 IEEE International Conference on Multimedia and Expo, ICME 2022 |
---|---|
City | Taipei, Taiwan |
Period | 18/07/22 → 22/07/22 |
Internet address |
User-Defined Keywords
- Long-tailed recognition
- class imbalance learning
- feature-balanced loss
- deep neural networks