The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition
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.
Code (1)
Tasks
image-classificationImage ClassificationLong-tailed Object Detectionobject-detectionObject DetectionObject RecognitionSemantic SegmentationSimilar Papers 제목 키워드 기반
Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection
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 m…
Instance SegmentationLong-tailed Object Detectionobject-detectionObject DetectionEqualization Loss for Long-Tailed Object Recognition
Object recognition techniques using convolutional neural networks (CNN) have achieved great success. However, state-of-the-art object detection methods still perform poorly on large vocabulary and long-tailed datasets, e…
Long-tail LearningObjectobject-detectionObject Detection+1End-to-end Optimization of Optical Communication Systems based on Directly Modulated Lasers
The use of directly modulated lasers (DMLs) is attractive in low-power, cost-constrained short-reach optical links. However, their limited modulation bandwidth can induce waveform distortion, undermining their data throu…
In-Context Learning for Non-Stationary MIMO Equalization
Channel equalization is fundamental for mitigating distortions such as frequency-selective fading and inter-symbol interference. Unlike standard supervised learning approaches that require costly retraining or fine-tunin…
Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism
Physics-Informed Neural Networks (PINNs) have emerged recently as a promising application of deep neural networks to the numerical solution of nonlinear partial differential equations (PDEs). However, it has been recogni…