paper-with-me

Papers Interactive Segmentation

“Interactive Segmentation” 태그가 달린 논문 305편 · 필터 해제

From Few-Shot Segmentation to Clinician-in-the-Loop Medical Image Analysis

2026-09-09 · Yazhou Zhu arxiv

Few-shot medical image segmentation (FSMIS) seeks to delineate unseen structures from a small support set, but its standard formulation fixes task-defining evidence before inference. This assumption is fragile when query…

Medical Image SegmentationInteractive SegmentationTest-time Adaptation

Prompt-Guided Interactive Segmentation of Interstitial Lung Disease in Thoracic CT

2026-08-28 · Vasilis Dedousis, Lubnaa Abdur Rahman, Lorenzo Brigatο, Ethan Dack 외 arxiv

Accurate segmentation of interstitial lung disease (ILD) patterns is essential for quantitative disease assessment and longitudinal monitoring. However, existing approaches remain limited by relying on dense annotations …

Interactive Segmentation

Prompt-Conditioned Channel Attention for Hierarchical Feature Modulation toward Anatomy-Agnostic Segmentation

2026-08-20 · Mosharof Hossain, Md Rabiul Islam, Limon Halder, Erchin Serpedin 외 arxiv

Anatomically plausible segmentation remains challenging because of low contrast, ambiguous boundaries, and modality-specific artifacts. Interactive segmentation has emerged as a promising strategy to guide feature extrac…

Medical Image SegmentationInteractive Segmentation

UniMedSeg: Unified In-Context Learning for Multi-Paradigm 2D/3D Medical Image Segmentation

2026-07-14 · Yunzhou Li, Jiesi Hu, Yanwu Yang, Hanyang Peng 외 arxiv

Medical image segmentation foundation models are expected to generalize across diverse clinical scenarios, yet existing universal methods remain fragmented by prompt paradigms and spatial dimensions. Visual in-context le…

Medical Image SegmentationInteractive Segmentation

Online Segment 3D Gaussians via Launching Virtual Drones

2026-07-02 · Liwei Liao, Rongjie Wang, Ronggang Wang arxiv

Interactive segmentation of 3D Gaussians offers a compelling opportunity for real-time manipulation of 3D scenes, thanks to the real-time rendering capability of 3D Gaussian Splatting (3DGS). However, existing methods re…

Interactive Segmentation

PGE-SAM: Prompt-Guided Feature Enhancement for Interactive Segmentation under Degradation

2026-06-29 · Tuan-Duc Nguyen, Anh-Tuan Mai, Duc-Trong Le arxiv

Segment Anything Model (SAM) has revolutionized promptable image segmentation with strong zero-shot generalization. However, its performance degrades substantially under real-world imaging artifacts such as noise, blur, …

Zero-shot GeneralizationInteractive SegmentationImage Segmentation

Temporal-Emerged Prompting for Segment Anything in Multiframe Infrared Small Target Detection

2026-06-26 · Yinghui Xing, Donghao Chu, Shizhou Zhang, Di Xu arxiv

Accurately localizing and segmenting small targets in low signal-to-noise ratio (SNR) infrared sequences remains a challenging task. Since targets are often indistinguishable from the background in individual frames, exi…

Interactive Segmentation

Prompting Diffusion Models for Zero-Shot Instance Segmentation

2026-06-21 · Irem Zeynep Alagöz, Nils Morbitzer, Andrea Ramazzina, Nassir Navab 외 arxiv

Several disruptive research directions have recently emerged in computer vision, including foundation models achieving previously unseen zero-shot performance in scene understanding, even interactively, and generative mo…

Interactive SegmentationInstance SegmentationScene Understanding

Human-in-the-Loop Atlas-Based 3D Asset Segmentation for Interactive Content Workflows

2026-06-16 · Paul Julius Kühn, Saptarshi Neil Sinha, Jakob Hansen, Robin Horst arxiv

Segmenting 3D assets into meaningful regions remains challenging, especially when segmentation criteria are application-dependent and require user control. We present a human-in-the-loop pipeline for generating a segment…

Interactive SegmentationStyle Transfer

One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation

2026-05-28 · Sanghyun Jo, Seo Jin Lee, Seohyung Hong, Yoorim Gang 외 arxiv

Cell instance segmentation models trained on cell-specific datasets suffer severe performance drops on out-of-distribution cell types, while interactive foundation models overcome this through per-instance prompting at a…

Interactive SegmentationInstance Segmentation

CLIP-Guided SAM: Parameter-Efficient Semantic Conditioning for Promptable Segmentation

2026-05-24 · Shayan Jalilian, Abdul Bais arxiv

Promptable foundation models such as the Segment Anything Model (SAM) produce high-quality masks but remain semantically blind, relying on external prompts to specify categories. Existing vision-language approaches addre…

Interactive Segmentation

SILSM: A Sustainable Interactive Level Set Method for Progressive Refinement

2026-05-23 · Jiachen Song, Dazhi Zhang, Fanghui Song, Zhichang Guo 외 arxiv

Interactive segmentation aims to precisely isolate target objects using sparse user guidance. However, traditional methods often suffer from heavy interaction burdens and parameter sensitivity, while deep learning approa…

Interactive Segmentation

ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings

2026-05-09 · Xueyang Kang, Zijian Yu, Kourosh Khoshelham, Liangliang Nan arxiv

Interactive segmentation allows efficient label generation by leveraging user-provided clicks to progressively refine predictions, which is critical when fully supervised labels are costly or generalization to unseen cla…

Interactive 3D Instance SegmentationInteractive Segmentation

MedP-CLIP: Medical CLIP with Region-Aware Prompt Integration

2026-04-13 · Jiahui Peng, He Yao, Jingwen Li, Yanzhou Su 외 arxiv

Contrastive Language-Image Pre-training (CLIP) has demonstrated outstanding performance in global image understanding and zero-shot transfer through large-scale text-image alignment. However, the core of medical image an…

Interactive Segmentation

From Static to Interactive: Adapting Visual in-Context Learners for User-Driven Tasks

2026-04-08 · Carlos Schmidt, Simon Reiß arxiv

Visual in-context learning models are designed to adapt to new tasks by leveraging a set of example input-output pairs, enabling rapid generalization without task-specific fine-tuning. However, these models operate in a …

Interactive SegmentationPose Estimation

PC-SAM: Patch-Constrained Fine-Grained Interactive Road Segmentation in High-Resolution Remote Sensing Images

2026-04-01 · Chengcheng Lv, Rushi Li, Mincheng Wu, Xiufang Shi 외 arxiv

Road masks obtained from remote sensing images effectively support a wide range of downstream tasks. In recent years, most studies have focused on improving the performance of fully automatic segmentation models for this…

Interactive SegmentationRoad Segmentation

Clore: Interactive Pathology Image Segmentation with Click-based Local Refinement

2026-03-29 · Tiantong Wang, Minfan Zhao, Jun Shi, Hannan Wang 외 arxiv

Recent advancements in deep learning-based interactive segmentation methods have significantly improved pathology image segmentation. Most existing approaches utilize user-provided positive and negative clicks to guide t…

Interactive SegmentationImage Segmentation

MagicSeg: Open-World Segmentation Pretraining via Counterfactural Diffusion-Based Auto-Generation

2026-03-20 · Kaixin Cai, Pengzhen Ren, Jianhua Han, Yi Zhu 외 arxiv

Open-world semantic segmentation presently relies significantly on extensive image-text pair datasets, which often suffer from a lack of fine-grained pixel annotations on sufficient categories. The acquisition of such da…

Interactive SegmentationSemantic SegmentationImage Generation

Speak, Segment, Track, Navigate: An Interactive System for Video-Guided Skull-Base Surgery

2026-03-17 · Jecia Z. Y. Mao, Francis X. Creighton, Russell H. Taylor, Manish Sahu arxiv

We introduce a speech-guided embodied agent framework for video-guided skull base surgery that dynamically executes perception and image-guidance tasks in response to surgeon queries. The proposed system integrates natur…

Interactive Segmentation

ActiveFreq: Integrating Active Learning and Frequency Domain Analysis for Interactive Segmentation

2026-03-12 · Lijun Guo, Qian Zhou, Zidi Shi, Hua Zou 외 arxiv

Interactive segmentation is commonly used in medical image analysis to obtain precise, pixel-level labeling, typically involving iterative user input to correct mislabeled regions. However, existing approaches often fail…

Interactive SegmentationActive Learning
1–20 / 305 다음 →