# Equalization Loss for Large Vocabulary Instance Segmentation

Source: [Equalization Loss for Large Vocabulary Instance Segmentation](<https://www.sota2.com/research/paper/68fa66ae1e209131cea11b1c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:56:21.324Z

Authors: Jingru Tan, Changbao Wang, Quanquan Li, Junjie Yan

Published: 2019-11-12T06:04:35.000Z

## Abstract

Recent object detection and instance segmentation tasks mainly focus on datasets with a relatively small set of categories, e.g. Pascal VOC with 20 classes and COCO with 80 classes. The new large vocabulary dataset LVIS brings new challenges to conventional methods. In this work, we propose an equalization loss to solve the long tail of rare categories problem. Combined with exploiting the data from detection datasets to alleviate the effect of missing-annotation problems during the training, our method achieves 5.1\\% overall AP gain and 11.4\\% AP gain of rare categories on LVIS benchmark without any bells and whistles compared to Mask R-CNN baseline. Finally we achieve 28.9 mask AP on the test-set of the LVIS and rank 1st place in LVIS Challenge 2019.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1911.04692>)

[PDF](<https://arxiv.org/pdf/1911.04692.pdf>)