๐
๐
Old Age
The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition
October 11, 2022 ยท Entered Twilight ยท ๐ IEEE Transactions on Pattern Analysis and Machine Intelligence
Repo contents: .flake8, .gitignore, LICENSE, README.md, benchmark, configs, docs, easy_setup.sh, requirements.txt, scripts, setup.py, up-logo.png, up
Authors
Jingru Tan, Bo Li, Xin Lu, Yongqiang Yao, Fengwei Yu, Tong He, Wanli Ouyang
arXiv ID
2210.05566
Category
cs.CV: Computer Vision
Citations
24
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Repository
https://github.com/ModelTC/United-Perception
โญ 436
Last Checked
1 month ago
Abstract
Long-tail distribution is widely spread in real-world applications. Due to the extremely small ratio of instances, tail categories often show inferior accuracy. In this paper, we find such performance bottleneck is mainly caused by the imbalanced gradients, which can be categorized into two parts: (1) positive part, deriving from the samples of the same category, and (2) negative part, contributed by other categories. Based on comprehensive experiments, it is also observed that the gradient ratio of accumulated positives to negatives is a good indicator to measure how balanced a category is trained. Inspired by this, we come up with a gradient-driven training mechanism to tackle the long-tail problem: re-balancing the positive/negative gradients dynamically according to current accumulative gradients, with a unified goal of achieving balance gradient ratios. Taking advantage of the simple and flexible gradient mechanism, we introduce a new family of gradient-driven loss functions, namely equalization losses. We conduct extensive experiments on a wide spectrum of visual tasks, including two-stage/single-stage long-tailed object detection (LVIS), long-tailed image classification (ImageNet-LT, Places-LT, iNaturalist), and long-tailed semantic segmentation (ADE20K). Our method consistently outperforms the baseline models, demonstrating the effectiveness and generalization ability of the proposed equalization losses. Codes will be released at https://github.com/ModelTC/United-Perception.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Computer Vision
๐
๐
Old Age
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
R.I.P.
๐ป
Ghosted
You Only Look Once: Unified, Real-Time Object Detection
๐
๐
Old Age
SSD: Single Shot MultiBox Detector
๐
๐
Old Age
Squeeze-and-Excitation Networks
R.I.P.
๐ป
Ghosted