AI Paper Atlas

Research map / Continual learning / Class-incremental

Unlocking Positive Transfer in Incrementally Learning Surgical Instruments: A Self-reflection Hierarchical Prompt Framework

Yu Zhu, Kang Li, Zheng Li, Pheng-Ann Heng

CVPR 2026 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 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 prompt framework (HPPT + SRS) to SAM (ablation)SAM ViT-H · EndoVis17->18 nephrectomyIoU (All): 48.15 -> 59.44Improved
add hierarchical prompt parsing tree (HPPT) (ablation)SAM ViT-H · EndoVis17->18 nephrectomyIoU (All): 48.15 -> 57.89Improved
add self-reflection refining strategy (SRS) on top of HPPT (ablation)SAM + HPPT · EndoVis17->18 nephrectomyIoU (All): 57.89 -> 59.44Improved
add SRS on top of HPPT (ablation)SAM + HPPT · EndoVis17->18 nephrectomy new classesIoU: 22.16 -> 22.30No clear effect
add SRS on top of HPPT (ablation)SAM + HPPT · EndoVis17->18 nephrectomy old classesIoU: 65.29 -> 68.52Improved
add HPPT to SAM for old classes (ablation)SAM ViT-H · EndoVis17->18 nephrectomy old classesIoU: 21.42 -> 65.29Improved
add HPPT to SAM for regular classes (ablation)SAM ViT-H · EndoVis17->18 nephrectomy regular classesIoU: 69.11 -> 69.23No clear effect
apply full framework to DeepLabv3+ backbone (ablation)DeepLabv3+ · EndoVis17->18 nephrectomyIoU (All): 27.62 -> 40.92Improved
use full framework instead of best prior CIL method (CAT-SD), same backboneDeepLabv3+ · EndoVis17->18 nephrectomyIoU (All): 35.09 -> 40.92Improved
use framework instead of CAT-SD on cholecystectomyDeepLabv3+ · CholecSeg8k->M2CAI-SegIoU (All): 48.93 -> 53.71Improved
use framework for positive backward transferDeepLabv3+ · EndoVis17->18 nephrectomyBWT: -0.88 -> 6.22Improved
add framework on SAM backbone for cholecystectomy FWTSAM ViT-H · CholecSeg8k->M2CAI-SegFWT: 0.69 (Ours SAM) vs 5.70 (Ours DeepLabv3+)Mixed

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