# Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment

arXiv: https://arxiv.org/abs/2305.11733 · HTML: https://mlsanity.com/paper/2305.11733/

## Key facts

- Cited by 75 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 42 references that are in the map.
- First posted on arXiv 19 May 2023.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [Equalization Loss for Long-Tailed Object Recognition](https://mlsanity.com/paper/2003.05176/) (2020)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [NormFace: L2 Hypersphere Embedding for Face Verification](https://mlsanity.com/paper/1704.06369/) (2017)
- [Improving Calibration for Long-Tailed Recognition](https://mlsanity.com/paper/2104.00466/) (2021)
- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [How Does Mixup Help With Robustness and Generalization?](https://mlsanity.com/paper/2010.04819/) (2020)
- [Disentangling Label Distribution for Long-tailed Visual Recognition](https://mlsanity.com/paper/2012.00321/) (2020)
- [Cost Sensitive Learning of Deep Feature Representations from Imbalanced Data](https://mlsanity.com/paper/1508.03422/) (2015)
- [Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification](https://mlsanity.com/paper/2103.14267/) (2021)
- [Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity](https://mlsanity.com/paper/2102.03065/) (2021)
- [The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation](https://mlsanity.com/paper/2007.11978/) (2020)
- [Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks](https://mlsanity.com/paper/1909.11515/) (2019)

## Built on by (most cited first, 30 of 75)

- [Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts](https://mlsanity.com/paper/2309.10019/) (2023)
- [Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding](https://mlsanity.com/paper/2403.18271/) (2024)
- [Probabilistic Contrastive Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2403.06726/) (2024)
- [A Systematic Review on Long-Tailed Learning](https://mlsanity.com/paper/2408.00483/) (2024)
- [Balancing Logit Variation for Long-tailed Semantic Segmentation](https://mlsanity.com/paper/2306.02061/) (2023)
- [A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization](https://mlsanity.com/paper/2310.04752/) (2023)
- [Out-of-Distribution Detection in Long-Tailed Recognition with Calibrated Outlier Class Learning](https://mlsanity.com/paper/2312.10686/) (2023)
- [Unbiased Scene Graph Generation via Two-stage Causal Modeling](https://mlsanity.com/paper/2307.05276/) (2023)
- [Feature Fusion from Head to Tail for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2306.06963/) (2023)
- [Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer](https://mlsanity.com/paper/2310.07587/) (2023)
- [Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2410.21042/) (2024)
- [DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets](https://mlsanity.com/paper/2404.02900/) (2024)
- [Balanced Destruction-Reconstruction Dynamics for Memory-replay Class Incremental Learning](https://mlsanity.com/paper/2308.01698/) (2023)
- [FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data](https://mlsanity.com/paper/2401.08977/) (2024)
- [Geometric Prior Guided Feature Representation Learning for Long-Tailed Classification](https://mlsanity.com/paper/2401.11436/) (2024)
- [A Comprehensive Survey on Imbalanced Data Learning](https://mlsanity.com/paper/2502.08960/) (2025)
- [Long-tailed Recognition with Model Rebalancing](https://mlsanity.com/paper/2510.08177/) (2025)
- [Deep Imbalanced Regression via Hierarchical Classification Adjustment](https://mlsanity.com/paper/2310.17154/) (2023)
- [Difficulty-aware Balancing Margin Loss for Long-tailed Recognition](https://mlsanity.com/paper/2412.15477/) (2024)
- [GeNIe: Generative Hard Negative Images Through Diffusion](https://mlsanity.com/paper/2312.02548/) (2023)
- [VLM-KD: Knowledge Distillation from VLM for Long-Tail Visual Recognition](https://mlsanity.com/paper/2408.16930/) (2024)
- [Towards Heterogeneous Long-tailed Learning: Benchmarking, Metrics, and Toolbox](https://mlsanity.com/paper/2307.08235/) (2023)
- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [Towards Unbiased and Robust Spatio-Temporal Scene Graph Generation and Anticipation](https://mlsanity.com/paper/2411.13059/) (2024)
- [Orthogonal Uncertainty Representation of Data Manifold for Robust Long-Tailed Learning](https://mlsanity.com/paper/2310.10090/) (2023)
- [Rectify the Regression Bias in Long-Tailed Object Detection](https://mlsanity.com/paper/2401.15885/) (2024)
- [LIFT+: Lightweight Fine-Tuning for Long-Tail Learning](https://mlsanity.com/paper/2504.13282/) (2025)
- [Curvature Learning for Generalization of Hyperbolic Neural Networks](https://mlsanity.com/paper/2508.17232/) (2025)
- [Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition](https://mlsanity.com/paper/2308.14024/) (2023)
- [Long-Tail Learning with Rebalanced Contrastive Loss](https://mlsanity.com/paper/2312.01753/) (2023)

## Abstract (arXiv)

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.