AMLRIS：用于指代图像分割的对齐感知掩码学习 / AMLRIS: Alignment-aware Masked Learning for Referring Image Segmentation
1️⃣ 一句话总结
这篇论文提出了一种名为对齐感知掩码学习的新训练方法，通过评估并过滤掉图像与文字描述之间对齐不佳的区域，让模型专注于可靠的视觉语言线索，从而在指代图像分割任务中取得了领先的性能，并增强了模型对不同描述和场景的适应能力。
arXiv 提交日期: 2026-02-26
Abstract - AMLRIS: Alignment-aware Masked Learning for Referring Image Segmentation
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
源自 arXiv: 2602.22740