AI Paper Atlas

Research map / Video / Video segmentation and tracking

FSD-Net: Foundation-Guided Spatiotemporal Distillation for Video Polyp Segmentation

Yahang Leng, Shiquan Min, Chengzhou Li

ECCV 2026 · Video › Video segmentation and tracking · approach: Video semantic and panoptic segmentation · 0 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 semantic flow distillation instead of optical flow propagation (ablation)FSD-Net baseline · SUN-SEG-HardmIoU: 64.88 -> 70.15Improved
add plain spatial knowledge distillation instead of optical flow (ablation)FSD-Net baseline · SUN-SEG-HardmIoU: 64.88 -> 67.52Improved
add standard cycle consistency on top of SFD (ablation)FSD-Net · SUN-SEG-HardmDice: 79.42 -> 78.56Hurt
add occlusion-aware cycle consistency (OACC) on top of SFD (ablation)FSD-Net · SUN-SEG-HardmDice: 79.42 -> 85.31Improved
add static prototype re-identification (ablation)FSD-Net (SFD+OACC) · SUN-SEG-HardmDice: 85.31 -> 85.35No clear effect
add momentum-updated PRM instead of static prototype (ablation)FSD-Net (SFD+OACC) · SUN-SEG-HardmDice: 85.31 -> 87.04Improved
use all three modules SFD, OACC and PRM together instead of a single module (ablation)FSD-Net · SUN-SEG-HardmDice: 79.56 -> 87.04Improved
prompt only the first frame instead of the middle frame only (ablation)FSD-Net · SUN-SEG-HardmDice: 83.20 -> 87.04Improved
add more prompted frames (first, middle, last) beyond the first frame (ablation)FSD-Net · SUN-SEG-HardmDice: 87.04 -> 86.10Hurt
supply one point prompt per frame at test time instead of prompt-free inferenceFSD-Net · SUN-SEG-HardmDice: 85.28 -> 87.04Improved
set visibility threshold to 0.80 instead of 0.60 (ablation)OACC · SUN-SEG-HardmDice: 84.66 -> 87.04Improved
FSD-Net with sparse annotation versus fully supervised Polyp-SAM-FSFSD-Net · SUN-SEG-HardmDice: 80.52 -> 87.04Improved

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