提出新方法让模型同时懂物体和上下文，提升真实场景下的识别鲁棒性。
Robust Context-Aware Object Recognition
- 先定位后识别，分离物体与上下文建模
- 在ImageNet-1k等数据集上提升性能，无需微调
- 适合需要兼顾准确与鲁棒的视觉应用
视觉识别中，目标物体（前景）与其周围环境（背景）均至关重要。然而，标准监督学习常导致模型过度依赖背景，产生虚假相关性的捷径学习，降低实际部署时的鲁棒性。现有方法多通过抑制背景来提升泛化能力，但牺牲了上下文信息。本文提出RCOR——鲁棒上下文感知物体识别，首个在不牺牲任一能力的前提下同时实现鲁棒性与上下文感知的方法。RCOR将定位视为识别的一部分，解耦物体中心与上下文感知建模，并采用鲁棒的非参数融合策略。该方法在包含域内与域外背景的数据集上，显著提升监督模型与视觉语言模型的表现，甚至无需微调。结果表明，在ImageNet-1k等复杂场景下，定位先行的识别已成为可能。
原文摘要 · Abstract (English)
In visual recognition, both the object of interest (referred to as foreground, FG, for simplicity) and its surrounding context (background, BG) play an important role. However, standard supervised learning often leads to unintended over-reliance on the BG, known as shortcut learning of spurious correlations, limiting model robustness in real-world deployment settings. In the literature, the problem is mainly addressed by suppressing the BG, sacrificing context information for improved generalization. We propose RCOR -- Robust Context-Aware Object Recognition -- the first approach that jointly achieves robustness and context-awareness without compromising either. RCOR treats localization as an integral part of recognition to decouple object-centric and context-aware modelling, followed by a robust, non-parametric fusion. It improves the performance of both supervised models and VLM on datasets with both in-domain and out-of-domain BG, even without fine-tuning. The results confirm that localization before recognition is now possible even in complex scenes as in ImageNet-1k.
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。