Learning to Label: A Reinforced Self-Evolving Framework for Semi-supervised Referring Expression Segmentation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916053867560960 |
|---|---|
| author | Cao, Runlong Zang, Ying Zhou, Chuanwei Chen, Tianrun Zhang, Tong Cui, Zhen Xu, Chunyan |
| author_facet | Cao, Runlong Zang, Ying Zhou, Chuanwei Chen, Tianrun Zhang, Tong Cui, Zhen Xu, Chunyan |
| contents | Semi-supervised referring expression segmentation (SS-RES) aims to achieve precise pixel-level language grounding under limited annotation, yet suffers from limited supervision and unreliable pseudo-labels when exploiting unlabeled image-text pairs. In this work, we propose Learning to Label, a reinforced self-evolving framework (L2L) that casts pseudo-label construction as a learnable decision-making process. To build foundational understanding, we leverage a multimodal large language model to extract semantic-spatial priors, which are instantiated as initial soft segmentation proposals and elevated, together with textual cues, into learnable guidance signals that condition a hierarchical segmentation network. To ensure stable learning, reinforced pseudo-label selection is formulated as an exploratory decision process that adaptively rewards high-utility pixel-level supervision based on multimodal priors and model predictions. This reinforced self-evolving loop enables joint optimization of the segmentation model and pseudo-labels, progressively enhancing label reliability under sparse supervision. Extensive experiments on RefCOCO, RefCOCO+, and RefCOCOg demonstrate improvements over existing methods, validating its effectiveness and generalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28239 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning to Label: A Reinforced Self-Evolving Framework for Semi-supervised Referring Expression Segmentation Cao, Runlong Zang, Ying Zhou, Chuanwei Chen, Tianrun Zhang, Tong Cui, Zhen Xu, Chunyan Computer Vision and Pattern Recognition Semi-supervised referring expression segmentation (SS-RES) aims to achieve precise pixel-level language grounding under limited annotation, yet suffers from limited supervision and unreliable pseudo-labels when exploiting unlabeled image-text pairs. In this work, we propose Learning to Label, a reinforced self-evolving framework (L2L) that casts pseudo-label construction as a learnable decision-making process. To build foundational understanding, we leverage a multimodal large language model to extract semantic-spatial priors, which are instantiated as initial soft segmentation proposals and elevated, together with textual cues, into learnable guidance signals that condition a hierarchical segmentation network. To ensure stable learning, reinforced pseudo-label selection is formulated as an exploratory decision process that adaptively rewards high-utility pixel-level supervision based on multimodal priors and model predictions. This reinforced self-evolving loop enables joint optimization of the segmentation model and pseudo-labels, progressively enhancing label reliability under sparse supervision. Extensive experiments on RefCOCO, RefCOCO+, and RefCOCOg demonstrate improvements over existing methods, validating its effectiveness and generalization. |
| title | Learning to Label: A Reinforced Self-Evolving Framework for Semi-supervised Referring Expression Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.28239 |