# Information Density Imbalance in Visual Object Detection

arXiv: https://arxiv.org/abs/2609.02369 · HTML: https://mlsanity.com/paper/2609.02369/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 44 of its 61 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Builds on (most cited first, 30 of 44)

- [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)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [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)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [Deep Learning for Generic Object Detection: A Survey](https://mlsanity.com/paper/1809.02165/) (2018)
- [Towards Open World Object Detection](https://mlsanity.com/paper/2103.02603/) (2021)
- [Equalization Loss for Long-Tailed Object Recognition](https://mlsanity.com/paper/2003.05176/) (2020)
- [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)
- [Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax](https://mlsanity.com/paper/2006.10408/) (2020)
- [Seesaw Loss for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2008.10032/) (2020)
- [Imbalance Problems in Object Detection: A Review](https://mlsanity.com/paper/1909.00169/) (2019)
- [Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1512.05830/) (2015)
- [The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation](https://mlsanity.com/paper/2007.11978/) (2020)
- [Long-Tailed Recognition via Weight Balancing](https://mlsanity.com/paper/2203.14197/) (2022)
- [A Survey of Deep Learning-based Object Detection](https://mlsanity.com/paper/1907.09408/) (2019)
- [The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification](https://mlsanity.com/paper/2112.00412/) (2021)
- [Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection](https://mlsanity.com/paper/2012.08548/) (2020)
- [FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2102.12867/) (2021)
- [A Survey on Long-Tailed Visual Recognition](https://mlsanity.com/paper/2205.13775/) (2022)
- [Learning Fast Sample Re-weighting Without Reward Data](https://mlsanity.com/paper/2109.03216/) (2021)
- [Adaptive Class Suppression Loss for Long-Tail Object Detection](https://mlsanity.com/paper/2104.00885/) (2021)
- [Exploring Classification Equilibrium in Long-Tailed Object Detection](https://mlsanity.com/paper/2108.07507/) (2021)

## Abstract (arXiv)

In object detection, the number of instances is typically used to determine whether a dataset exhibits a long-tailed distribution, implicitly assuming that the model will perform poorly on categories with fewer instances. This assumption has led to extensive research on category bias in datasets with imbalanced instance numbers. However, even in datasets where instance numbers are relatively balanced, models still exhibit category bias, indicating that instance count alone cannot explain this phenomenon. In this work, we first introduce the concept and measurement of information density. We then observe a significant negative correlation between a category's information density and its accuracy, and we investigate how the training process impacts this relationship. Empirical studies suggest that information density imbalance may be a potential source of category bias. To preliminarily validate the potential of information density, we made simple improvements to three advanced object detection loss functions using this concept. Experiments on the Pascal VOC, COCO-LT, and LVIS datasets demonstrate that information density can significantly reduce model bias while effectively enhancing the overall performance of existing loss functions. This study provides a new perspective for understanding the generalized bias phenomenon in object detection models and offers new tools for designing fairer loss functions and training strategies.