# FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation

Source: [FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation](<https://www.sota2.com/research/paper/68fa6ef21e209131cea43168>)

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

Data updated: 2026-01-04T04:29:22.582Z

Authors: Junjie He, Pengyu Li, Yifeng Geng, Xuansong Xie

Published: 2023-03-15T13:06:30.000Z

## Abstract

Recent attention in instance segmentation has focused on query-based models. Despite being non-maximum suppression (NMS)-free and end-to-end, the superiority of these models on high-accuracy real-time benchmarks has not been well demonstrated. In this paper, we show the strong potential of query-based models on efficient instance segmentation algorithm designs. We present FastInst, a simple, effective query-based framework for real-time instance segmentation. FastInst can execute at a real-time speed (i.e., 32.5 FPS) while yielding an AP of more than 40 (i.e., 40.5 AP) on COCO test-dev without bells and whistles. Specifically, FastInst follows the meta-architecture of recently introduced Mask2Former. Its key designs include instance activation-guided queries, dual-path update strategy, and ground truth mask-guided learning, which enable us to use lighter pixel decoders, fewer Transformer decoder layers, while achieving better performance. The experiments show that FastInst outperforms most state-of-the-art real-time counterparts, including strong fully convolutional baselines, in both speed and accuracy. Code can be found at https://github.com/junjiehe96/FastInst .

## 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.

- [Instance Segmentation on COCO (test-dev)](<https://www.sota2.com/research/sota/instance-segmentation-on-coco-test-dev.md>): Instance Segmentation; COCO (test-dev); APM: 57.9.

- [Instance Segmentation on LIACI](<https://www.sota2.com/research/sota/instance-segmentation-on-liaci.md>): Instance Segmentation; LIACI; mAP: 38.6.

- [Instance Segmentation on ZeroWaste (test)](<https://www.sota2.com/research/sota/instance-segmentation-on-zerowaste-test.md>): Instance Segmentation; ZeroWaste (test); mAP: 27.5.

- [Instance Segmentation on Cityscapes (val)](<https://www.sota2.com/research/sota/instance-segmentation-on-cityscapes-val.md>): Instance Segmentation; Cityscapes (val); AP: 35.5.

- [Panoptic Segmentation on Cityscapes (val)](<https://www.sota2.com/research/sota/panoptic-segmentation-on-cityscapes-val.md>): Panoptic Segmentation; Cityscapes (val); PQ: 56.4.

- [Semantic Segmentation on Cityscapes (val) (mIoU only)](<https://www.sota2.com/research/sota/semantic-segmentation-on-cityscapes-val-miou-only.md>): Semantic segmentation; Cityscapes (val); mIoU: 74.7.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2303.08594>)

[PDF](<https://arxiv.org/pdf/2303.08594.pdf>)

[Implementation](<https://github.com/junjiehe96/FastInst>)