AMLRIS: Alignment-aware Masked Learning for Referring Image Segmentation

Tongfei Chen, Shuo Yang, Yuguang Yang, Linlin Yang, Runtang Guo +5 more
2/26/2026
cs.CVcs.AI

No confident code implementation found for this paper.

Abstract

Referring Image Segmentation (RIS) aims to segment an object in an image identified by a natural language expression. The paper introduces Alignment-Aware Masked Learning (AML), a training strategy to enhance RIS by explicitly estimating pixel-level vision-language alignment, filtering out poorly aligned regions during optimization, and focusing on trustworthy cues. This approach results in state-of-the-art performance on RefCOCO datasets and also enhances robustness to diverse descriptions and scenarios

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation

83% match2026

Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation

83% match1 repo142023

GenSeg-R1: RL-Driven Vision-Language Grounding for Fine-Grained Referring Segmentation

83% match1 repo42026

Prompt-Driven Referring Image Segmentation with Instance Contrasting

81% match2026

MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation

81% match1 repo182024

Shatter and Gather: Learning Referring Image Segmentation with Text Supervision

81% match1 repo442026

Cite this paper

@article{chen2026amlris,
  title  = {AMLRIS: Alignment-aware Masked Learning for Referring Image Segmentation},
  author = {Tongfei Chen and Shuo Yang and Yuguang Yang and Linlin Yang and Runtang Guo and Changbai Li and He Long and Chunyu Xie and Dawei Leng and Baochang Zhang},
  year   = {2026},
  eprint = {2602.22740},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2602.22740v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2602.22740.svg)](https://codeofpaper.com/paper/2602.22740)

Discussion