可变形注意力视觉增强用于基于视觉语言模型的指代分割
Deformable Attentive Visual Enhancement for Referring Segmentation Using Vision-Language Model
AI总结：
提出SegVLM视觉语言模型，通过集成SE块、可变形卷积和残差连接，并引入指代感知融合损失，提升指代分割精度与跨模态对齐，实验证明各组件有效且泛化性强。
摘要：
图像分割是计算机视觉中的一项基本任务，旨在将图像划分为语义上有意义的区域。指代图像分割通过使用自然语言表达来定位特定对象，扩展了这一任务，需要有效整合视觉和语言信息。在这项工作中，我们提出了SegVLM，一种视觉语言模型，它融入了架构改进以提升分割精度和跨模态对齐。该模型集成了压缩-激励（SE）块用于动态特征重校准，可变形卷积用于几何适应性，以及残差连接用于深度特征学习。我们还引入了一种新颖的指代感知融合（RAF）损失函数，它平衡了区域级对齐、边界精度和类别不平衡。广泛的实验和消融研究表明，每个组件都对性能的一致提升有所贡献。SegVLM还展示了在多样化数据集和指代表达场景中的强大泛化能力。
英文摘要：
Image segmentation is a fundamental task in computer vision, aimed at partitioning an image into semantically meaningful regions. Referring image segmentation extends this task by using natural language expressions to localize specific objects, requiring effective integration of visual and linguistic information. In this work, we propose SegVLM, a vision-language model that incorporates architectural improvements to enhance segmentation accuracy and cross-modal alignment. The model integrates squeeze-and-excitation (SE) blocks for dynamic feature recalibration, deformable convolutions for geometric adaptability, and residual connections for deep feature learning. We also introduce a novel referring-aware fusion (RAF) loss that balances region-level alignment, boundary precision, and class imbalance. Extensive experiments and ablation studies demonstrate that each component contributes to consistent performance improvements. SegVLM also shows strong generalization across diverse datasets and referring expression scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
