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 disjointed 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 this paper, we reveal the main issue in long-tailed object detection is the imbalanced gradients between positives and negatives, and find that EQL does not solve it well. To address the problem of imbalanced gradients, we introduce a new version of equalization loss, called equalization loss v2 (EQL v2), a novel gradient guided reweighing mechanism that re-balances the training process for each category independently and equally. Extensive experiments are performed on the challenging LVIS benchmark. EQL v2 outperforms origin EQL by about 4 points overall AP with 14-18 points improvements on the rare categories. More importantly, It also surpasses decoupled training methods. Without further tuning for the Open Images dataset, EQL v2 improves EQL by 6.3 points AP, showing strong generalization ability. Codes will be released at https://github.com/tztztztztz/eqlv2

为解决不平衡梯度导致的长尾目标检测困难，本研究提出了一种新的均衡损失（EQL v2）。实验结果表明，EQL v2 在 LVIS 基准测试中表现优异，比起原 EQL 可提高 4 个点的总 AP 值和 14-18 个点的罕见类别 AP 值，并且甚至超过了分离式训练方法。

Equalization Loss v2: 长尾物体检测的新梯度平衡方法