Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
arXiv:2103.16370
Abstract
Despite the recent success of deep neural networks, it remains challenging to effectively model the long-tail class distribution in visual recognition tasks. To address this problem, we first investigate the performance bottleneck of the two-stage learning framework via ablative study. Motivated by our discovery, we propose a unified distribution alignment strategy for long-tail visual recognition. Specifically, we develop an adaptive calibration function that enables us to adjust the classification scores for each data point. We then introduce a generalized re-weight method in the two-stage learning to balance the class prior, which provides a flexible and unified solution to diverse scenarios in visual recognition tasks. We validate our method by extensive experiments on four tasks, including image classification, semantic segmentation, object detection, and instance segmentation. Our approach achieves the state-of-the-art results across all four recognition tasks with a simple and unified framework. The code and models will be made publicly available at: https://github.com/Megvii-BaseDetection/DisAlign
Accepted by CVPR 2021
References in corpus (6)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Rethinking Atrous Convolution for Semantic Image Segmentation
- A systematic study of the class imbalance problem in convolutional neural networks
- Data Augmentation for Object Detection via Progressive and Selective Instance-Switching
- Solution for Large-Scale Hierarchical Object Detection Datasets with Incomplete Annotation and Data Imbalance