Nah, Wan Jun and Ng, Chun Chet and Lin, Che-Tsung and Lee, Yeong Khang and Kew, Jie Long and Tan, Zhi Qin and Chan, Chee Seng and Zach, Christopher and Lai, Shang-Hong (2023) Rethinking Long-Tailed Visual Recognition with Dynamic Probability Smoothing and Frequency Weighted Focusing. In: 2023 IEEE International Conference on Image Processing (ICIP), 8-11 October 2023, Kuala Lumpur, Malaysia.
Full text not available from this repository.Abstract
Deep learning models trained on long-tailed (LT) datasets often exhibit bias towards head classes with high frequency. This paper highlights the limitations of existing solutions that combine class- and instance-level re-weighting loss in a naive manner. Specifically, we demonstrate that such solutions result in overfitting the training set, significantly impacting the rare classes. To address this issue, we propose a novel loss function that dynamically reduces the influence of outliers and assigns class-dependent focusing parameters. We also introduce a new long-tailed dataset, ICText-LT, featuring various image qualities and greater realism than artificially sampled datasets. Our method has proven effective, outperforming existing methods through superior quantitative results on CIFAR-LT, Tiny ImageNet-LT, and our new ICText-LT datasets. The source code and new dataset are available at https://github.com/nwjun/FFDS-Loss.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Funders: | UNSPECIFIED |
| Additional Information: | 30th IEEE International Conference on Image Processing (ICIP), Kuala Lumpur, MALAYSIA, OCT 08-11, 2023 |
| Uncontrolled Keywords: | Long-tailed Classification; Weighted-loss |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Faculty of Computer Science & Information Technology |
| Depositing User: | Ms. Juhaida Abd Rahim |
| Date Deposited: | 18 Sep 2025 06:20 |
| Last Modified: | 18 Sep 2025 06:20 |
| URI: | http://eprints.um.edu.my/id/eprint/50493 |
Actions (login required)
 |
View Item |
