A hierarchical prompt tree with self-reflection graph propagation enables positive forward and backward knowledge transfer in incremental surgical instrument segmentation, improving over baselines by more than 5% and 11% on two benchmarks.
Cholecseg8k: a semantic segmentation dataset for laparoscopic cholecystectomy based on cholec80
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
DenseTRF adapts texture-aware representations via slot attention for unsupervised improvement of cross-domain generalization in surgical dense prediction tasks.
citing papers explorer
-
Unlocking Positive Transfer in Incrementally Learning Surgical Instruments: A Self-reflection Hierarchical Prompt Framework
A hierarchical prompt tree with self-reflection graph propagation enables positive forward and backward knowledge transfer in incremental surgical instrument segmentation, improving over baselines by more than 5% and 11% on two benchmarks.
-
DenseTRF: Texture-Aware Unsupervised Representation Adaptation for Surgical Scene Dense Prediction
DenseTRF adapts texture-aware representations via slot attention for unsupervised improvement of cross-domain generalization in surgical dense prediction tasks.