# Classification Calibration for Long-tail Instance Segmentation

arXiv: https://arxiv.org/abs/1910.13081 · HTML: https://mlsanity.com/paper/1910.13081/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2019.

## Built on by (most cited first, 4 of 4)

- [On Model Calibration for Long-Tailed Object Detection and Instance Segmentation](https://mlsanity.com/paper/2107.02170/) (2021)
- [Class-Difficulty Based Methods for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2207.14499/) (2022)
- [Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining](https://mlsanity.com/paper/2210.08375/) (2022)
- [TMI: Text-to-Image Meets Image-to-Image for Complementary Data Synthesis to Boost Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2607.08201/) (2026)

## Abstract (arXiv)

Remarkable progress has been made in object instance detection and segmentation in recent years. However, existing state-of-the-art methods are mostly evaluated with fairly balanced and class-limited benchmarks, such as Microsoft COCO dataset [8]. In this report, we investigate the performance drop phenomenon of state-of-the-art two-stage instance segmentation models when processing extreme long-tail training data based on the LVIS [5] dataset, and find a major cause is the inaccurate classification of object proposals. Based on this observation, we propose to calibrate the prediction of classification head to improve recognition performance for the tail classes. Without much additional cost and modification of the detection model architecture, our calibration method improves the performance of the baseline by a large margin on the tail classes. Codes will be available. Importantly, after the submission, we find significant improvement can be further achieved by modifying the calibration head, which we will update later.