No article text was recorded for this version.
prompt sensitivity (spatial prompt sensitivity)
Version 1 of 170 papers85 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Segment Anything Model for Medical Images?
- Blog: Stable Segment Anything Model
- Blog: Segment Anything Model for Medical Image Segmentation: Current Applications and Future Directions
- Blog: MedSAM-U: Uncertainty-Guided Auto Multi-Prompt Adaptation for Reliable MedSAM
- Blog: Robust Box Prompt based SAM for Medical Image Segmentation
- Blog: A Unified Framework for 3D Scene Understanding
- Blog: TETRIS: Towards Exploring the Robustness of Interactive Segmentation
- Blog: Segment Anything Model Can Not Segment Anything: Assessing AI Foundation Model's Generalizability in Permafrost Mapping
- Blog: SAMAug: Point Prompt Augmentation for Segment Anything Model
- Blog: RClicks: Realistic Click Simulation for Benchmarking Interactive Segmentation
- Blog: Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imaging
- Blog: Research on Medical Image Segmentation Based on SAM and Its Future Prospects
- Blog: Assessing Test-time Variability for Interactive 3D Medical Image Segmentation with Diverse Point Prompts
- Blog: Plug-and-Play PPO: An Adaptive Point Prompt Optimizer Making SAM Greater
- Blog: Interactive Segmentation and Report Generation for CT Images
- Blog: Domesticating SAM for Breast Ultrasound Image Segmentation via Spatial-Frequency Fusion and Uncertainty Correction
- Blog: Slide-SAM: Medical SAM Meets Sliding Window
- Blog: FocSAM: Delving Deeply into Focused Objects in Segmenting Anything
- Blog: Mastering SAM Prompts: A Large-Scale Empirical Study in Segmentation Refinement for Scientific Imaging
- Blog: Tuning vision foundation models for rectal cancer segmentation from CT scans
- Blog: Towards Training-Free Open-World Segmentation via Image Prompt Foundation Models
- Blog: One-Prompt to Segment All Medical Images
- Blog: Semi-Automated Segmentation of Microbes in Color Images
- Blog: Geodesic Thin Plate Splines for Image Segmentation
- Blog: PP-SAM: Perturbed Prompts for Robust Adaptation of Segment Anything Model for Polyp Segmentation
- Blog: HyperFree: A Channel-adaptive and Tuning-free Foundation Model for Hyperspectral Remote Sensing Imagery
- Blog: SeedNet: Automatic Seed Generation With Deep Reinforcement Learning for Robust Interactive Segmentation
- Blog: Open-Vocabulary RGB-Thermal Semantic Segmentation
- Blog: SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation
- Blog: SAM-Med3D: Towards General-Purpose Segmentation Models for Volumetric Medical Images
- Blog: PromptPilot: Game-Theoretic Multi-Agent Prompt Optimization for Segment Anything
- Blog: ProSAM: Enhancing the Robustness of SAM-based Visual Reference Segmentation with Probabilistic Prompts
- Blog: Register Anything: Estimating "Corresponding Prompts" for Segment Anything Model
- Blog: Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning
- Blog: Explore Synergistic Interaction Across Frames for Interactive Video Object Segmentation
- Blog: Evaluation study on SAM 2 for class-agnostic instance-level segmentation
- Blog: Rethinking and Improving Visual Prompt Selection for In-Context Learning Segmentation Framework
- Blog: MedSAM-U: Uncertainty-Guided Auto Multi-Prompt Adaptation for Reliable MedSAM
- Blog: Few Exemplar-Based General Medical Image Segmentation via Domain-Aware Selective Adaptation
- Blog: DB-SAM: Delving into High Quality Universal Medical Image Segmentation
- Blog: Polyp SAM 2: Advancing Zero-Shot Polyp Segmentation in Colorectal Cancer Detection
- Blog: Multi-modal Segment Anything Model for Camouflaged Scene Segmentation
- Blog: A Unified Framework for 3D Scene Understanding
- Blog: E-BayesSAM: Efficient Bayesian Adaptation of SAM with Self-Optimizing KAN-Based Interpretation for Uncertainty-Aware Ultrasonic Segmentation
- Blog: DarkSAM: Fooling Segment Anything Model to Segment Nothing
- Blog: SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement
- Blog: Improving semi-automated segmentation by integrating learning with active sampling
- Blog: Interactive Object Segmentation With Inside-Outside Guidance
- Blog: Cross Prompting Consistency with Segment Anything Model for Semi-supervised Medical Image Segmentation
- Blog: TETRIS: Towards Exploring the Robustness of Interactive Segmentation
- Blog: Flaws can be Applause: Unleashing Potential of Segmenting Ambiguous Objects in SAM
- Blog: Segment anything model for medical images?
- Blog: Zero-Shot Medical Image Segmentation Based on Sparse Prompt Using Finetuned SAM
- Blog: Guided SAM: Label-Efficient Part Segmentation
- Blog: Robust interactive image segmentation via graph-based manifold ranking
- Blog: HyperFree: A Channel-adaptive and Tuning-free Foundation Model for Hyperspectral Remote Sensing Imagery
- Blog: SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement
- Blog: Stability of AI-Enabled Diagnosis of Parkinson’s Disease: A Study Targeting Substantia Nigra in Quantitative Susceptibility Mapping Imaging
- Blog: RP-SAM2: Refining Point Prompts for Stable Surgical Instrument Segmentation
- Blog: Evaluation of Segment Anything Model 2: The Role of SAM2 in the Underwater Environment
Showing 60 of 70 papers.
History & citation
Current · Permanent link
- This direction split from Robust Interactive Segmentation via Prompt Stability (89% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_prompt_sensitivity_spatial_prompt_sensit_b346273a,
title = {prompt sensitivity (spatial prompt sensitivity)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/prompt-sensitivity-spatial-prompt-sensitivity/rdr_b346273a986447d287d878aab4ba2dd6},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_prompt_sensitivity_spatial_prompt_sensit_b346273a_v1,
title = {prompt sensitivity (spatial prompt sensitivity)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/prompt-sensitivity-spatial-prompt-sensitivity/rdr_b346273a986447d287d878aab4ba2dd6/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}