# Margin Calibration for Long-Tailed Visual Recognition

arXiv: https://arxiv.org/abs/2112.07225 · HTML: https://mlsanity.com/paper/2112.07225/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 52 references that are in the map.
- First posted on arXiv 14 Dec 2021.

## Builds on (most cited first, 29 of 29)

- [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)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (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)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [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)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [Equalization Loss for Long-Tailed Object Recognition](https://mlsanity.com/paper/2003.05176/) (2020)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [What is the Effect of Importance Weighting in Deep Learning?](https://mlsanity.com/paper/1812.03372/) (2018)
- [Rethinking the Value of Labels for Improving Class-Imbalanced Learning](https://mlsanity.com/paper/2006.07529/) (2020)
- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [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)
- [Seesaw Loss for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2008.10032/) (2020)
- [Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective](https://mlsanity.com/paper/2003.10780/) (2020)
- [Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification](https://mlsanity.com/paper/2103.14267/) (2021)
- [Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1512.05830/) (2015)
- [Large Margin Deep Networks for Classification](https://mlsanity.com/paper/1803.05598/) (2018)
- [The Devil is in the Tails: Fine-grained Classification in the Wild](https://mlsanity.com/paper/1709.01450/) (2017)
- [RSG: A Simple but Effective Module for Learning Imbalanced Datasets](https://mlsanity.com/paper/2106.09859/) (2021)
- [Deep Over-sampling Framework for Classifying Imbalanced Data](https://mlsanity.com/paper/1704.07515/) (2017)
- [Adjusting Decision Boundary for Class Imbalanced Learning](https://mlsanity.com/paper/1912.01857/) (2019)
- [The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis](https://mlsanity.com/paper/2009.07022/) (2020)

## Built on by (most cited first, 17 of 17)

- [PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization](https://mlsanity.com/paper/2306.05087/) (2023)
- [USB: A Unified Semi-supervised Learning Benchmark for Classification](https://mlsanity.com/paper/2208.07204/) (2022)
- [A Survey on Long-Tailed Visual Recognition](https://mlsanity.com/paper/2205.13775/) (2022)
- [A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation](https://mlsanity.com/paper/2402.04087/) (2024)
- [Exploring Vision-Language Models for Imbalanced Learning](https://mlsanity.com/paper/2304.01457/) (2023)
- [Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks](https://mlsanity.com/paper/2309.17002/) (2023)
- [An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2211.11086/) (2022)
- [Difficulty-aware Balancing Margin Loss for Long-tailed Recognition](https://mlsanity.com/paper/2412.15477/) (2024)
- [Impact of Noisy Supervision in Foundation Model Learning](https://mlsanity.com/paper/2403.06869/) (2024)
- [RAHNet: Retrieval Augmented Hybrid Network for Long-tailed Graph Classification](https://mlsanity.com/paper/2308.02335/) (2023)
- [CDMPP: A Device-Model Agnostic Framework for Latency Prediction of Tensor Programs](https://mlsanity.com/paper/2311.09690/) (2023)
- [Prior2Posterior: Model Prior Correction for Long-Tailed Learning](https://mlsanity.com/paper/2412.16540/) (2024)
- [Text-Guided Mixup Towards Long-Tailed Image Categorization](https://mlsanity.com/paper/2409.03583/) (2024)
- [CALA: A Class-Aware Logit Adapter for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2412.12654/) (2024)
- [Mixture of Balanced Information Bottlenecks for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2509.01804/) (2025)
- [Why Not Hyperparameter-Friendly Optimisation? A Monotonic Adaptive Norm Rescaling Approach For Long-Tailed Recognition](https://mlsanity.com/paper/2606.02526/) (2026)
- [StrokeTimer: Robust Representation Learning for Ischemic Stroke Onset-Time Estimation from Non-contrast CT](https://mlsanity.com/paper/2606.04722/) (2026)

## Abstract (arXiv)

The long-tailed class distribution in visual recognition tasks poses great challenges for neural networks on how to handle the biased predictions between head and tail classes, i.e., the model tends to classify tail classes as head classes. While existing research focused on data resampling and loss function engineering, in this paper, we take a different perspective: the classification margins. We study the relationship between the margins and logits (classification scores) and empirically observe the biased margins and the biased logits are positively correlated. We propose MARC, a simple yet effective MARgin Calibration function to dynamically calibrate the biased margins for unbiased logits. We validate MARC through extensive experiments on common long-tailed benchmarks including CIFAR-LT, ImageNet-LT, Places-LT, and iNaturalist-LT. Experimental results demonstrate that our MARC achieves favorable results on these benchmarks. In addition, MARC is extremely easy to implement with just three lines of code. We hope this simple method will motivate people to rethink the biased margins and biased logits in long-tailed visual recognition.