Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment

Abstract

Long-tailed data is still a big challenge for deep neural networks, even though they have achieved great success on balanced data. We observe that vanilla training on long-tailed data with cross-entropy loss makes the instance-rich head classes severely squeeze the spatial distribution of the tail classes, which leads to difficulty in classifying tail class samples. Furthermore, the original cross-entropy loss can only propagate gradient short-lively because the gradient in softmax form rapidly approaches zero as the logit difference increases. This phenomenon is called softmax saturation. It is unfavorable for training on balanced data, but can be utilized to adjust the validity of the samples in long-tailed data, thereby solving the distorted embedding space of long-tailed problems. To this end, this paper proposes the Gaussian clouded logit adjustment by Gaussian perturbation of different class logits with varied amplitude. We define the amplitude of perturbation as cloud size and set relatively large cloud sizes to tail classes. The large cloud size can reduce the softmax saturation and thereby making tail class samples more active as well as enlarging the embedding space. To alleviate the bias in a classifier, we therefore propose the class-based effective number sampling strategy with classifier re-training. Extensive experiments on benchmark datasets validate the superior performance of the proposed method. Source code is available at https://github.com/Keke921/GCLLoss.

arXiv commentPublished as a conference paper at CVPR 2022. arXiv admin note: text overlap with arXiv:2305.10648

References in corpus (6)

• mixup: Beyond Empirical Risk Minimization
• Understanding Black-box Predictions via Influence Functions
• Learning to Reweight Examples for Robust Deep Learning
• NormFace: L2 Hypersphere Embedding for Face Verification
• Deep Long-Tailed Learning: A Survey
• Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks

Cited by in corpus (5)

• Feature Fusion from Head to Tail for Long-Tailed Visual Recognition
• DBN-Mix: Training Dual Branch Network Using Bilateral Mixup Augmentation for Long-Tailed Visual Recognition
• Adjusting Logit in Gaussian Form for Long-Tailed Visual Recognition
• A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization
• Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition