Salvato in:
Dettagli Bibliografici
Autori principali: Vetoshkin, Luka, Yudin, Dmitry
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.05396
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908395387224064
author Vetoshkin, Luka
Yudin, Dmitry
author_facet Vetoshkin, Luka
Yudin, Dmitry
contents Segmenting objects with complex shapes, such as wires, bicycles, or structural grids, remains a significant challenge for current segmentation models, including the Segment Anything Model (SAM) and its high-quality variant SAM-HQ. These models often struggle with thin structures and fine boundaries, leading to poor segmentation quality. We propose Talk2SAM, a novel approach that integrates textual guidance to improve segmentation of such challenging objects. The method uses CLIP-based embeddings derived from user-provided text prompts to identify relevant semantic regions, which are then projected into the DINO feature space. These features serve as additional prompts for SAM-HQ, enhancing its ability to focus on the target object. Beyond improving segmentation accuracy, Talk2SAM allows user-controllable segmentation, enabling disambiguation of objects within a single bounding box based on textual input. We evaluate our approach on three benchmarks: BIG, ThinObject5K, and DIS5K. Talk2SAM consistently outperforms SAM-HQ, achieving up to +5.9\% IoU and +8.3\% boundary IoU improvements. Our results demonstrate that incorporating natural language guidance provides a flexible and effective means for precise object segmentation, particularly in cases where traditional prompt-based methods fail. The source code is available on GitHub: https://github.com/richlukich/Talk2SAM
format Preprint
id arxiv_https___arxiv_org_abs_2506_05396
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Talk2SAM: Text-Guided Semantic Enhancement for Complex-Shaped Object Segmentation
Vetoshkin, Luka
Yudin, Dmitry
Computer Vision and Pattern Recognition
Image and Video Processing
Segmenting objects with complex shapes, such as wires, bicycles, or structural grids, remains a significant challenge for current segmentation models, including the Segment Anything Model (SAM) and its high-quality variant SAM-HQ. These models often struggle with thin structures and fine boundaries, leading to poor segmentation quality. We propose Talk2SAM, a novel approach that integrates textual guidance to improve segmentation of such challenging objects. The method uses CLIP-based embeddings derived from user-provided text prompts to identify relevant semantic regions, which are then projected into the DINO feature space. These features serve as additional prompts for SAM-HQ, enhancing its ability to focus on the target object. Beyond improving segmentation accuracy, Talk2SAM allows user-controllable segmentation, enabling disambiguation of objects within a single bounding box based on textual input. We evaluate our approach on three benchmarks: BIG, ThinObject5K, and DIS5K. Talk2SAM consistently outperforms SAM-HQ, achieving up to +5.9\% IoU and +8.3\% boundary IoU improvements. Our results demonstrate that incorporating natural language guidance provides a flexible and effective means for precise object segmentation, particularly in cases where traditional prompt-based methods fail. The source code is available on GitHub: https://github.com/richlukich/Talk2SAM
title Talk2SAM: Text-Guided Semantic Enhancement for Complex-Shaped Object Segmentation
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2506.05396