CVPR Findings2026
OKGraph: Online Knowledge Graph Probing for Open-vocabulary Recognition
Junhui Yin, Zhizhen Cai, Puze Wang, Guanzhou Ke, Jianhua Yang, Man Zhang, Qiang Zhang, Shengfeng He
摘要
Vision-language models (VLMs) have made significant strides in open-vocabulary recognition by aligning visual inputs with textual representations. However, most existing approaches treat categories as independent labels and rely on prompt tuning or feature adaptation, overlooking the underlying semantic structure that links related concepts. This lack of semantic connectivity limits the models' ability to generalize, especially when the data distribution shifts or categories exhibit semantic ambiguity, where recognizing instances often depends on understanding their relationships to known concepts. We propose Online Knowledge Graph Probing (OKGraph), a dynamic framework that constructs, updates, and applies a semantic knowledge graph to guide recognition. OKGraph integrates the perceptual capabilities of VLMs with the semantic reasoning of large language models (LLMs), enabling the adaptive extraction of contextual knowledge from test data. Through iterative contextual probing and model-guided correction, OKGraph refines its knowledge graph without requiring any training data or manual annotations. Extensive experiments across diverse vision tasks and domains demonstrate that OKGraph substantially improves zero-shot and few-shot performance, highlighting the value of structured reasoning in open-world vision. The code is available at https://github.com/zenithc-git/OKGraph.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
脉络
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation 引用了 Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation 引用了 Learning Transferable Visual Models From Natural Language Supervision
- Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision 引用了 The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization
- Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision 引用了 Learning Transferable Visual Models From Natural Language Supervision
- Learning Transferable Visual Models From Natural Language Supervision 引用了 The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization
- Flamingo: a Visual Language Model for Few-Shot Learning 引用了 BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
- Flamingo: a Visual Language Model for Few-Shot Learning 引用了 Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
- Flamingo: a Visual Language Model for Few-Shot Learning 引用了 Learning Transferable Visual Models From Natural Language Supervision
它引用的 Paper24
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 47,906 次引用
- Flamingo: a Visual Language Model for Few-Shot LearningJean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech 等NeurIPS 2022 · 6,707 次引用
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and GenerationJunnan Li, Dongxu Li, Caiming Xiong, Steven C. H. HoiICML 2022 · 6,549 次引用
- Scaling Up Visual and Vision-Language Representation Learning With Noisy Text SupervisionChao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen 等ICML 2021 · 5,401 次引用
- The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution GeneralizationDan Hendrycks, Steven Basart, Norman Mu, Saurav Kadavath 等ICCV 2021 · 2,294 次引用
相关 Paper
- Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language ModelYushu Li, Yongyi Su, Adam Goodge, Kui Jia 等ICLR 2025
- LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image CollectionsMuhammad Jehanzeb Mirza, Leonid Karlinsky, Wei Lin, Horst Possegger 等NeurIPS 2023 · 63 次引用
- View-on-Graph: Zero-Shot 3D Visual Grounding via Vision-Language Reasoning on Scene GraphsYuanyuan Liu, Haiyang Mei, Dongyang Zhan, Jiayue Zhao 等AAAI 2026 · 1 次引用
- Tree of Attributes Prompt Learning for Vision-Language ModelsTong Ding, Wanhua Li, Zhongqi Miao, Hanspeter PfisterICLR 2025
- Open-World 3D Scene Graph Generation for Retrieval-Augmented ReasoningFei Yu, Quan Deng, Shengeng Tang, Yuehua Li 等AAAI 2026 · 2 次引用
