FlowSeg: Dynamic Semantic Guidance for LLM-Conditioned Segmentation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918528989265920 |
|---|---|
| author | Zhang, Zekang Gao, Guangyu Tang, Youyun Wu, ChengJing Qu, Xiaochao Liu, Chi Harold Jiao, Jianbo Wei, Yunchao Liu, Luoqi Liu, Ting |
| author_facet | Zhang, Zekang Gao, Guangyu Tang, Youyun Wu, ChengJing Qu, Xiaochao Liu, Chi Harold Jiao, Jianbo Wei, Yunchao Liu, Luoqi Liu, Ting |
| contents | LLM-conditioned segmentation has recently advanced rapidly by coupling large language models with iterative mask generation frameworks. However, we identify a persistent failure mode in current propose-then-select pipelines. Although high-quality mask candidates are often generated, the final prediction may fail to match the given linguistic condition. This failure arises because language semantics are typically used as static prompts or post-hoc matching signals, rather than participating in the iterative mask generation process. Through systematic analysis, we show that many errors stem from semantic misalignment rather than poor mask quality. To address this issue, we propose FlowSeg, which introduces dynamic semantic guidance via a bidirectional semantic flow between intermediate decoding states and LLM-derived condition embeddings throughout the generation process. Language conditions actively guide mask refinement at each stage, while condition embeddings are progressively updated by emerging visual evidence. This design yields semantically grounded mask representations and visually aligned language conditions, enabling more reliable matching. We further incorporate a lightweight boundary-aware refinement to selectively enhance uncertain regions without perturbing confident interiors. Extensive experiments on referring expression segmentation and reasoning segmentation tasks demonstrate that FlowSeg consistently improves language-mask alignment and achieves state-of-the-art performance. Project page: https://zkzhang98.github.io/FlowSeg_page |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29461 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FlowSeg: Dynamic Semantic Guidance for LLM-Conditioned Segmentation Zhang, Zekang Gao, Guangyu Tang, Youyun Wu, ChengJing Qu, Xiaochao Liu, Chi Harold Jiao, Jianbo Wei, Yunchao Liu, Luoqi Liu, Ting Computer Vision and Pattern Recognition LLM-conditioned segmentation has recently advanced rapidly by coupling large language models with iterative mask generation frameworks. However, we identify a persistent failure mode in current propose-then-select pipelines. Although high-quality mask candidates are often generated, the final prediction may fail to match the given linguistic condition. This failure arises because language semantics are typically used as static prompts or post-hoc matching signals, rather than participating in the iterative mask generation process. Through systematic analysis, we show that many errors stem from semantic misalignment rather than poor mask quality. To address this issue, we propose FlowSeg, which introduces dynamic semantic guidance via a bidirectional semantic flow between intermediate decoding states and LLM-derived condition embeddings throughout the generation process. Language conditions actively guide mask refinement at each stage, while condition embeddings are progressively updated by emerging visual evidence. This design yields semantically grounded mask representations and visually aligned language conditions, enabling more reliable matching. We further incorporate a lightweight boundary-aware refinement to selectively enhance uncertain regions without perturbing confident interiors. Extensive experiments on referring expression segmentation and reasoning segmentation tasks demonstrate that FlowSeg consistently improves language-mask alignment and achieves state-of-the-art performance. Project page: https://zkzhang98.github.io/FlowSeg_page |
| title | FlowSeg: Dynamic Semantic Guidance for LLM-Conditioned Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.29461 |