Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Learning to Label: A Reinforced Self-Evolving Framework for Semi-supervised Referring Expression Segmentation

About

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.

Runlong Cao, Ying Zang, Chuanwei Zhou, Tianrun Chen, Tong Zhang, Zhen Cui, Chunyan Xu• 2026

Related benchmarks

TaskDatasetResultRank
Referring Expression SegmentationRefCOCO (testA)--
315
Referring Expression SegmentationRefCOCO+ (testA)--
288
Referring Expression SegmentationRefCOCO+ (val)--
272
Referring Expression SegmentationRefCOCO (val)--
261
Referring Expression SegmentationRefCOCO (testB)--
259
Referring Expression SegmentationRefCOCO+ (testB)--
256
Referring Expression SegmentationRefCOCOg (val (U))--
95
Referring Expression SegmentationRefCOCOg (test(U))--
78
Referring Expression SegmentationRefCOCOg UMD (val)
mIoU60.63
52
Referring Expression SegmentationRefCOCOg UMD (test-u)
mIoU62.66
46
Showing 10 of 15 rows

Other info

Follow for update