arXiv：cs.AI· Zhengtao Zou, Pekka Marttinen·· 16 小时前
视觉语言模型看得见深度却选择线索：VLM 深度判断中的线索冲突研究
Seeing Depth but Choosing Cues in Vision-Language Models
AI 导读
研究发现视觉语言模型在深度判断中会系统性偏向误导性的图像平面线索（如视觉大小和垂直位置），但正确的深度顺序仍可从被查询对象的视觉表征中解码出来，即便模型答错时也是如此。通过对象级写回强化模型自身的深度读出，可在不更新模型参数、不使用真实深度标注的情况下纠正冲突决策，但该校正效果取决于写入信号的方向和目标 token，强度因架构和领域而异。
正文
Abstract:Do vision-language models use depth information to judge which object is closer, or rely on image-plane cues? We investigate this question through controlled depth--cue conflicts, representation analysis, and interventions. Among the many image-plane cues relevant to depth perception, we focus on apparent size and vertical position. We compare depth judgments under cue-consistent and cue-conflict conditions in both rendered scenes and real-world photographs. Across model families and scales, depth judgments systematically shift toward misleading cues. Yet the correct depth order remains decodable from the queried objects' visual representations, including when the model answers incorrectly. Image and category controls support interpreting this signal as image-dependent depth information beyond the two target cues. Strengthening the model's own depth readout through object-level write-back can correct conflict decisions without updating model parameters or using ground-truth depth annotations. Interventions show that the effect of this correction depends on the direction and target tokens of the written signal, while its strength varies across architectures and domains. Together, these findings reveal a mismatch between a model's ability to represent depth and use this information when deciding the answer. VLMs can retain useful depth information while allowing competing image-plane cues to exert greater influence on their answers.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.17976 [cs.AI] |
| (or arXiv:2610.17976v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17976 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhengtao Zou [view email]
[v1]
Tue, 13 Oct 2026 08:49:04 UTC (7,081 KB)
来源：arXiv：cs.AI · arxiv.org