Distribution Alignment: A Unified Framework for Long-tail Visual Recognition

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

PDF Abstract CVPR 2021 PDF CVPR 2021 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Long-tail Learning ImageNet-LT DisAlign Top-1 Accuracy 53.4 # 24
Long-tail Learning iNaturalist 2018 DisAlign Top-1 Accuracy 70.6% # 16
Long-tail Learning Places-LT DisAlign Top-1 Accuracy 39.3 # 12

Methods


No methods listed for this paper. Add relevant methods here