# Adaptive Logit Adjustment Loss for Long-Tailed Visual Recognition

arXiv: https://arxiv.org/abs/2104.06094 · HTML: https://mlsanity.com/paper/2104.06094/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 13 Apr 2021.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (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)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (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)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [Large-Margin Softmax Loss for Convolutional Neural Networks](https://mlsanity.com/paper/1612.02295/) (2016)
- [Equalization Loss for Long-Tailed Object Recognition](https://mlsanity.com/paper/2003.05176/) (2020)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [Long-tailed Recognition by Routing Diverse Distribution-Aware Experts](https://mlsanity.com/paper/2010.01809/) (2020)
- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification](https://mlsanity.com/paper/2001.01536/) (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)

## Built on by (most cited first, 30 of 33)

- [Retrieval Augmented Classification for Long-Tail Visual Recognition](https://mlsanity.com/paper/2202.11233/) (2022)
- [LPT: Long-tailed Prompt Tuning for Image Classification](https://mlsanity.com/paper/2210.01033/) (2022)
- [Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts](https://mlsanity.com/paper/2309.10019/) (2023)
- [A survey on learning from imbalanced data streams: taxonomy, challenges, empirical study, and reproducible experimental framework](https://mlsanity.com/paper/2204.03719/) (2022)
- [Learning Imbalanced Data with Vision Transformers](https://mlsanity.com/paper/2212.02015/) (2022)
- [A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization](https://mlsanity.com/paper/2310.04752/) (2023)
- [When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method](https://mlsanity.com/paper/2211.10955/) (2022)
- [Unbiased Scene Graph Generation via Two-stage Causal Modeling](https://mlsanity.com/paper/2307.05276/) (2023)
- [FedIIC: Towards Robust Federated Learning for Class-Imbalanced Medical Image Classification](https://mlsanity.com/paper/2206.13803/) (2022)
- [Delving into the Trajectory Long-tail Distribution for Muti-object Tracking](https://mlsanity.com/paper/2403.04700/) (2024)
- [NCL++: Nested Collaborative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2306.16709/) (2023)
- [A Causal Adjustment Module for Debiasing Scene Graph Generation](https://mlsanity.com/paper/2503.17862/) (2025)
- [Difficulty-aware Balancing Margin Loss for Long-tailed Recognition](https://mlsanity.com/paper/2412.15477/) (2024)
- [Taming the Long Tail in Human Mobility Prediction](https://mlsanity.com/paper/2410.14970/) (2024)
- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Tasks](https://mlsanity.com/paper/2407.08567/) (2024)
- [Revisiting Long-tailed Image Classification: Survey and Benchmarks with New Evaluation Metrics](https://mlsanity.com/paper/2302.01507/) (2023)
- [Fractal Calibration for long-tailed object detection](https://mlsanity.com/paper/2410.11774/) (2024)
- [LIFT+: Lightweight Fine-Tuning for Long-Tail Learning](https://mlsanity.com/paper/2504.13282/) (2025)
- [Long-Tail Temporal Action Segmentation with Group-wise Temporal Logit Adjustment](https://mlsanity.com/paper/2408.09919/) (2024)
- [Implicit Counterfactual Data Augmentation for Robust Learning](https://mlsanity.com/paper/2304.13431/) (2023)
- [General vs. Long-Tailed Age Estimation: An Approach to Kill Two Birds with One Stone](https://mlsanity.com/paper/2307.10129/) (2023)
- [Data-Centric Long-Tailed Image Recognition](https://mlsanity.com/paper/2311.01744/) (2023)
- [BAPE: Learning an Explicit Bayes Classifier for Long-tailed Visual Recognition](https://mlsanity.com/paper/2506.23280/) (2025)
- [LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups](https://mlsanity.com/paper/2511.10683/) (2025)
- [Class Instance Balanced Learning for Long-Tailed Classification](https://mlsanity.com/paper/2307.05322/) (2023)
- [DASA: Difficulty-Aware Semantic Augmentation for Speaker Verification](https://mlsanity.com/paper/2310.12111/) (2023)
- [Normalizing Batch Normalization for Long-Tailed Recognition](https://mlsanity.com/paper/2501.03122/) (2025)
- [Cost-Sensitive Learning for Long-Tailed Temporal Action Segmentation](https://mlsanity.com/paper/2503.18358/) (2025)
- [Mitigating Spurious Correlations with Causal Logit Perturbation](https://mlsanity.com/paper/2505.15246/) (2025)

## Abstract (arXiv)

Data in the real world tends to exhibit a long-tailed label distribution, which poses great challenges for the training of neural networks in visual recognition. Existing methods tackle this problem mainly from the perspective of data quantity, i.e., the number of samples in each class. To be specific, they pay more attention to tail classes, like applying larger adjustments to the logit. However, in the training process, the quantity and difficulty of data are two intertwined and equally crucial problems. For some tail classes, the features of their instances are distinct and discriminative, which can also bring satisfactory accuracy; for some head classes, although with sufficient samples, the high semantic similarity with other classes and lack of discriminative features will bring bad accuracy. Based on these observations, we propose Adaptive Logit Adjustment Loss (ALA Loss) to apply an adaptive adjusting term to the logit. The adaptive adjusting term is composed of two complementary factors: 1) quantity factor, which pays more attention to tail classes, and 2) difficulty factor, which adaptively pays more attention to hard instances in the training process. The difficulty factor can alleviate the over-optimization on tail yet easy instances and under-optimization on head yet hard instances. The synergy of the two factors can not only advance the performance on tail classes even further, but also promote the accuracy on head classes. Unlike previous logit adjusting methods that only concerned about data quantity, ALA Loss tackles the long-tailed problem from a more comprehensive, fine-grained and adaptive perspective. Extensive experimental results show that our method achieves the state-of-the-art performance on challenging recognition benchmarks, including ImageNet-LT, iNaturalist 2018, and Places-LT.