AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Multi-granularity Interaction Simulation for Unsupervised Interactive Segmentation

Kehan Li, Yian Zhao, Zhennan Wang, Zesen Cheng, Peng Jin, Xiangyang Ji, Li Yuan, Chang Liu, Jie Chen

ICCV 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 8 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 multi-granularity proposals (decay coefficient 0.9 versus 0.0) (ablation)MIS · DAVISNoC@90: 9.92 -> 8.44Improved
add multi-granularity proposals (alpha 0.9 versus 0.0) (ablation)MIS · SBDNoC@90: 10.87 -> 9.51Improved
add smoothness constraint (ablation)MIS · DAVISNoC@90: 10.08 -> 8.44Improved
add smoothness constraint (ablation)MIS · BerkeleyNoC@90: 5.51 -> 4.58Improved
use top-down sampling instead of uniform sampling of tree nodes (ablation)MIS · GrabCutNoC@90: 4.32 -> 2.32Improved
use top-down sampling instead of uniform sampling (ablation)MIS · DAVISNoC@90: 10.10 -> 8.44Improved
add connectivity constraint in bottom-up merging (ablation)MIS · preprocessing speedimages/s: 1.10 -> 3.73Improved
add connectivity constraint in bottom-up merging (ablation)MIS · SBD / BerkeleyNoC@90: 9.46 -> 9.51 (SBD NoC@90)No clear effect
add connectivity constraint in bottom-up merging (ablation)MIS · DAVISNoC@90: 7.56 -> 8.44Hurt
increase decay coefficient to 0.95 (ablation)MIS · GrabCutNoC@90: 2.32 -> 2.62Hurt
increase smoothness weight lambda to 15.0 (ablation)MIS · DAVISNoC@90: 8.44 -> 9.10Hurt
use MIS pretraining instead of MAE init with 1% labelsSimpleClick-style model · SBD (1% labels)NoC@90: 10.43 -> 8.15Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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