AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

TokenCut: Segmenting Objects in Images and Videos With Self-Supervised Transformer and Normalized Cut

Yangtao Wang, Xi Shen, Yuan Yuan, Yuming Du, Maomao Li, Shell Xu Hu, James L. Crowley, Dominique Vaufreydaz

TPAMI 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 124 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
add CRF edge refinement (ablation)TokenCut · ECSSD (saliency)IoU (%): 71.2 -> 77.7Improved
add CRF edge refinement (ablation)TokenCut (RAFT flow) · DAVIS (video)Jaccard index: 64.3 -> 76.7Improved
use self-supervised DINO instead of supervised DeiT (ablation)TokenCut · VOC07 (object discovery)CorLoc: 2.39 -> 68.8Improved
use DINO instead of MoCoV3 (ablation)TokenCut · VOC07 (object discovery)CorLoc: 66.2 -> 68.8Improved
use DINO-B/16 instead of MAE-B/16 (ablation)TokenCut · VOC07 (object discovery)CorLoc: 61.5 -> 68.8Improved
use patch size 16 instead of 8 (ablation)TokenCut · VOC07 (object discovery)CorLoc: 67.3 -> 68.8No clear effect
increase tau from 0 to 0.3 (ablation)TokenCut · DAVIS (video)Jaccard index: 70.7 -> 76.7Improved
use mean split instead of EM (ablation)TokenCut · VOC07 (object discovery)CorLoc: 63.0 -> 68.8Improved
use mean split instead of K-means (ablation)TokenCut · COCO20KCorLoc: 58.8 -> 61.6Mixed
add optical flow to RGB in graph (ablation)TokenCut · DAVIS (video, CRF)Jaccard index: 62.2 -> 76.7Improved
add optical flow to RGB in graph (ablation)TokenCut · FBMS (video, CRF)Jaccard index: 67.5 -> 66.6Hurt
use transformer features of flow instead of mean flow (ablation)TokenCut · DAVIS (video, CRF)Jaccard index: 37.5 -> 76.7Improved

Later papers that compared with this method

17 later accepted papers report TokenCut as a baseline in their results tables; 17 of them report a better number on most of the results they share with it.

9 more not listed.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

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