AI Paper Atlas

Research map / Detection and segmentation / CNN features

SegGPT: Towards Segmenting Everything in Context

Xinlong Wang, Xiaosong Zhang, Yue Cao, Wen Wang, Chunhua Shen, Tiejun Huang

ICCV 2023 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 545 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use feature ensemble instead of spatial ensemble for multiple examples (ablation)SegGPT · DAVIS 2017J&F: 61.9 -> 74.7Improved
use feature ensemble instead of spatial ensemble on low-resolution data (ablation)SegGPT · FSS-1000mIoU: 89.3 -> 87.8Hurt
use 4 example frames with feature ensemble instead of 1 (ablation)SegGPT · DAVIS 2017J&F: 70.0 -> 74.7Improved
increase context frames from 8 to 16 (ablation)SegGPT · DAVIS 2017J&F: 75.6 -> 74.6Hurt
use random color mapping in in-context training instead of fixed task colorsSegGPT · ADE20K semantic segmentationmIoU: Painter 49.9 -> SegGPT 39.6Hurt
use random color mapping in in-context training instead of fixed task colorsSegGPT · COCO panoptic segmentationPQ: Painter 43.4 -> SegGPT 34.4Hurt
use random coloring and mixed training instead of Painter's fixed colorsSegGPT · FSS-1000 one-shot (out-of-domain)mIoU: 61.7 -> 85.6Improved
use random coloring and mixed training instead of PainterSegGPT · YouTube-VOS 2018G: 24.1 -> 74.7Improved
use SegGPT versus specialist VOS models trained on video dataSegGPT · YouTube-VOS 2018G: SegGPT 74.7 vs XMem 86.1, AGAME 66.0Mixed

Later papers that compared with this method

12 later accepted papers report SegGPT as a baseline in their results tables; 9 of them report a better number on most of the results they share with it.

4 more not listed.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy