Real-world data tends to follow a long-tailed distribution, where the class imbalance results in dominance of the head classes during training. In this paper, we propose a frustratingly simple but effective step-wise learning framework to gradually enhance the capability of the model in detecting all categories of long-tailed datasets. Specifically, we build smooth-tail data where the long-tailed distribution of categories decays smoothly to correct the bias towards head classes. We pre-train a model on the whole long-tailed data to preserve discriminability between all categories. We then fine-tune the class-agnostic modules of the pre-trained model on the head class dominant replay data to get a head class expert model with improved decision boundaries from all categories. Finally, we train a unified model on the tail class dominant replay data while transferring knowledge from the head class expert model to ensure accurate detection of all categories. Extensive experiments on long-tailed datasets LVIS v0.5 and LVIS v1.0 demonstrate the superior performance of our method, where we can improve the AP with ResNet-50 backbone from 27.0% to 30.3% AP, and especially for the rare categories from 15.5% to 24.9% AP. Our best model using ResNet-101 backbone can achieve 30.7% AP, which suppresses all existing detectors using the same backbone.

翻译：现实世界的数据往往服从长尾分布，其中类别不平衡导致训练过程中头部类别占据主导地位。本文提出一种极其简单但有效的分步学习框架，逐步提升模型检测长尾数据集中所有类别的能力。具体而言，我们构建了类别长尾分布平滑衰减的平滑尾数据，以矫正模型对头部类别的偏置。首先在完整长尾数据上预训练模型以保持所有类别间的判别性。随后，在头部类别主导的重放数据上微调预训练模型的类无关模块，获得具有更优决策边界的头部类别专家模型。最后，在尾部类别主导的重放数据上训练统一模型，同时迁移头部类别专家模型的知识，确保对所有类别的精确检测。在长尾数据集LVIS v0.5和LVIS v1.0上的大量实验表明，本方法性能优异：采用ResNet-50骨干网络时，AP从27.0%提升至30.3%，其中稀有类别AP从15.5%提升至24.9%。使用ResNet-101骨干网络的最佳模型可达到30.7%的AP，超越所有采用相同骨干网络的现有检测器。