# Long-tailed Instance Segmentation using Gumbel Optimized Loss

arXiv: https://arxiv.org/abs/2207.10936 · HTML: https://mlsanity.com/paper/2207.10936/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 44 references that are in the map.
- First posted on arXiv 22 Jul 2022.

## Builds on (most cited first, 30 of 34)

- [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)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (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)
- [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)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [Hybrid Task Cascade for Instance Segmentation](https://mlsanity.com/paper/1901.07518/) (2019)
- [Cascade R-CNN: High Quality Object Detection and Instance Segmentation](https://mlsanity.com/paper/1906.09756/) (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)
- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [Cost Sensitive Learning of Deep Feature Representations from Imbalanced Data](https://mlsanity.com/paper/1508.03422/) (2015)
- [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)
- [Probabilistic two-stage detection](https://mlsanity.com/paper/2103.07461/) (2021)
- [Imbalance Problems in Object Detection: A Review](https://mlsanity.com/paper/1909.00169/) (2019)
- [The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation](https://mlsanity.com/paper/2007.11978/) (2020)
- [Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection](https://mlsanity.com/paper/2012.08548/) (2020)
- [Adaptive Class Suppression Loss for Long-Tail Object Detection](https://mlsanity.com/paper/2104.00885/) (2021)
- [Adjusting Decision Boundary for Class Imbalanced Learning](https://mlsanity.com/paper/1912.01857/) (2019)
- [Exploring Classification Equilibrium in Long-Tailed Object Detection](https://mlsanity.com/paper/2108.07507/) (2021)
- [Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation](https://mlsanity.com/paper/2008.05676/) (2020)

## Built on by (most cited first, 12 of 12)

- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [A Systematic Review on Long-Tailed Learning](https://mlsanity.com/paper/2408.00483/) (2024)
- [HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation](https://mlsanity.com/paper/2303.15994/) (2023)
- [Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning](https://mlsanity.com/paper/2404.03323/) (2024)
- [Instance-Aware Repeat Factor Sampling for Long-Tailed Object Detection](https://mlsanity.com/paper/2305.08069/) (2023)
- [Inverse Image Frequency for Long-tailed Image Recognition](https://mlsanity.com/paper/2209.04861/) (2022)
- [Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Tasks](https://mlsanity.com/paper/2407.08567/) (2024)
- [Rectify the Regression Bias in Long-Tailed Object Detection](https://mlsanity.com/paper/2401.15885/) (2024)
- [Fractal Calibration for long-tailed object detection](https://mlsanity.com/paper/2410.11774/) (2024)
- [Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition](https://mlsanity.com/paper/2308.14024/) (2023)
- [A Benchmark of Long-tailed Instance Segmentation with Noisy Labels](https://mlsanity.com/paper/2211.13435/) (2022)
- [PAT: Pixel-wise Adaptive Training for Long-tailed Segmentation](https://mlsanity.com/paper/2404.05393/) (2024)

## Abstract (arXiv)

Major advancements have been made in the field of object detection and segmentation recently. However, when it comes to rare categories, the state-of-the-art methods fail to detect them, resulting in a significant performance gap between rare and frequent categories. In this paper, we identify that Sigmoid or Softmax functions used in deep detectors are a major reason for low performance and are sub-optimal for long-tailed detection and segmentation. To address this, we develop a Gumbel Optimized Loss (GOL), for long-tailed detection and segmentation. It aligns with the Gumbel distribution of rare classes in imbalanced datasets, considering the fact that most classes in long-tailed detection have low expected probability. The proposed GOL significantly outperforms the best state-of-the-art method by 1.1% on AP , and boosts the overall segmentation by 9.0% and detection by 8.0%, particularly improving detection of rare classes by 20.3%, compared to Mask-RCNN, on LVIS dataset. Code available at: https://github.com/kostas1515/GOL