重新审视 LVLM 中的视觉损坏：从形状-纹理视角看模型失效
Revisiting Visual Corruptions in LVLMs: A Shape-Texture Perspective on Model Failures
提出免训练的对比解码框架 ST-CD，通过构造形状与纹理互补的对比视图并在推理时自适应融合来纠正偏置，可直接迁移到任何 LVLM 的推理阶段以提升对视觉损坏的鲁棒性，无需微调。
原文依据 we propose Shape-Texture Dual-Path Contrastive Decoding (ST-CD), a training-free inference framework
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论大型视觉语言模型（LVLM）极易受到视觉损坏的影响，这严重损害了其可靠性并限制了实际部署。已有工作主要将这种性能退化归因于视觉定位不足以及对语言先验的过度依赖。然而，这些解释往往忽略了损坏的异质性——不同类型的损坏以根本不同的方式扰动模型感知。我们从以损坏为中心的视角重新审视该问题，并表明多样化的损坏可以沿两个互补的感知维度——形状与纹理——加以组织，二者会诱发不同的失效模式。为解决这些问题，我们提出形状-纹理双路径对比解码（ST-CD），这是一个免训练的推理框架，它构造互补的对比视图，并通过自适应融合来诊断和纠正由形状与纹理诱发的偏置。在多个 LVLM 与鲁棒性基准上的实验表明，ST-CD 在异质损坏下持续提升鲁棒性，这表明利用形状与纹理之间的互补性为构建鲁棒的多模态模型提供了一条通用而有效的原则。
英文原文摘要 1202 字符
Large vision-language models (LVLMs) are highly vulnerable to visual corruptions, substantially compromising their reliability and limiting real-world deployment. Prior work has attributed this degradation primarily to insufficient visual grounding and overreliance on language priors. However, these explanations often overlook the heterogeneous nature of corruptions, which perturb model perception in fundamentally different ways. We revisit this problem from a corruption-centric perspective and show that diverse corruptions can be organized along two complementary perceptual dimensions--shape and texture--which induce distinct failure modes. To address them, we propose Shape-Texture Dual-Path Contrastive Decoding (ST-CD), a training-free inference framework that constructs complementary contrastive views to diagnose and correct shape- and texture-induced biases through adaptive fusion. Experiments across multiple LVLMs and robustness benchmarks demonstrate that ST-CD consistently improves robustness under heterogeneous corruptions, suggesting that leveraging the complementarity between shape and texture provides a general and effective principle for building robust multimodal models.