Weight-guided class complementing for long-tailed image recognition
Real-world data are often long-tailed distributed and have plenty classes. This characteristic leads to a significant performance drop for various models. One reason behind that is the gradient shift caused by unsampled classes in each training iteration. In this paper, we propose a Weight-Guided Class Complementing framework to address this issue. Specifically, this framework first complements the unsampled classes in each training iteration by using a dynamic updated data slot. Then, considering the over-fitting issue caused by class complementing, we utilize the classifier weights as learned knowledge and encourage the model to discover more class specific characteristics. Finally, we design a weight refining scheme to deal with the long-tailed bias existing in classifier weights. Experimental results show that our framework can be implemented upon different existing approaches effectively, achieving consistent improvements on various benchmarks with new state-of-the-art performances.
PDF AbstractTasks
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Long-tail Learning | CIFAR-100-LT (ρ=100) | LDAM-DRW + WGCC | Error Rate | 56.4 | # 53 | |
Long-tail Learning | CIFAR-100-LT (ρ=100) | NCL* + WGCC (ensemble) | Error Rate | 44.9 | # 12 | |
Long-tail Learning | CIFAR-10-LT (ρ=100) | NCL* + WGCC (ensemble) | Error Rate | 15.4 | # 11 |