# Towards Good Practices for Instance Segmentation

Source: [Towards Good Practices for Instance Segmentation](<https://www.sota2.com/research/paper/68fa66ab1e209131cea118ca>)

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

Data updated: 2025-10-25T21:55:21.281Z

Authors: Dongdong Yu, Zehuan Yuan, Jinlai Liu, Kun Yuan, Changhu Wang

Published: 2019-10-28T03:03:48.000Z

## Abstract

Instance Segmentation is an interesting yet challenging task in computer vision. In this paper, we conduct a series of refinements with the Hybrid Task Cascade (HTC) Network, and empirically evaluate their impact on the final model performance through ablation studies. By taking all the refinements, we achieve 0.47 on the COCO test-dev dataset and 0.47 on the COCO test-challenge dataset.

## 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/1911.07939>)

[PDF](<https://arxiv.org/pdf/1911.07939.pdf>)