Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection
Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection
Recently proposed decoupled training methods emerge as a dominant paradigm for long-tailed object detection. But they require an extra fine-tuning stage, and the dis-jointed optimization of representation and classifier might lead to suboptimal results. However, end-to-end training methods, like equalization loss (EQL), still perform worse than decoupled training methods. In …