解析多模态大模型分割能力的衰减与恢复机制
From Drop-off to Recovery: A Mechanistic Analysis of Segmentation in MLLMs
- 分层探查视觉编码器、适配器和语言模型各阶段表示
- 适配器导致分割表示下降，语言模型层通过注意力逐步恢复
- 适合关注多模态模型视觉推理机制的研究者
多模态大语言模型（MLLM）在像素级视觉任务中应用日益广泛，但其对空间理解的内在能力仍不明确。我们通过全管道分层线性探查评估：视觉编码器、适配器和语言模型。进一步开展基于注意力剔除的干预分析，检验跨标记注意力是否逐步优化视觉表征，并评估图像标记间双向注意力对空间一致性的贡献。结果表明，适配器引入了分割表征的衰减，但语言模型层通过注意力介导的精炼实现逐步恢复，正确分类的标记能引导误分类邻居转向正确标签。在早期图像标记位置，这种恢复受限于因果注意力，而图像标记间的双向注意力可缓解该限制。这些发现为MLLM处理分割任务的机制提供了机理解释，有助于未来分割能力模型的设计。
原文摘要 · Abstract (English)
Multimodal Large Language Models (MLLMs) are increasingly applied to pixel-level vision tasks, yet their intrinsic capacity for spatial understanding remains poorly understood. We investigate segmentation capacity through a layerwise linear probing evaluation across the entire MLLM pipeline: vision encoder, adapter, and LLM. We further conduct an intervention based attention knockout analysis to test whether cross-token attention progressively refines visual representations, and an evaluation of bidirectional attention among image tokens on spatial consistency. Our analysis reveals that the adapter introduces a segmentation representation drop-off, but LLM layers progressively recover through attention-mediated refinement, where correctly classified tokens steer misclassified neighbors toward the correct label. At early image token positions, this recovery is bounded by causal attention, which bidirectional attention among image tokens alleviates. These findings provide a mechanistic account of how MLLMs process visual information for segmentation, informing the design of future segmentation-capable models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。