Research map / Vision-language and multimodal / CLIP and zero-shot
ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling
William Yicheng Zhu, Keren Ye, Junjie Ke, Jiahui Yu, Leonidas Guibas, Peyman Milanfar, Feng Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use generative retrieval instead of contrastive retrieval | CoCa Base · VAW zero-shot | average rank: 95.1 -> 56.0 | Improved |
| use generative retrieval instead of contrastive retrieval after finetuning | CoCa Base · VAW finetuned | average rank: 12.2 -> 10.6 | Improved |
| add object hint to contrastive retrieval sentence (ablation) | Contrastive retrieval · VAW zero-shot | average rank: 95.1 -> 149.8 | Hurt |
| use object-conditioned sentence {A}{O} instead of attribute-only {A} in generative retrieval (ablation) | Generative retrieval · VAW zero-shot | average rank: 82.1 -> 63.9 | Improved |
| use hybrid template {A}{O} is {A} instead of {O} is {A} (ablation) | Generative retrieval · VAW zero-shot | average rank: 61.9 -> 56.0 | Improved |
| use hybrid template {A}{O} is {A} on object recognition instead of {A}{O} (ablation) | Generative retrieval · VGARank-Object zero-shot | rank: 5.8 -> 6.4 | Hurt |
| use hybrid template on attribute recognition (ablation) | Generative retrieval · VGARank-Attribute zero-shot | rank: 13.0 -> 12.0 | Improved |
| use generative retrieval instead of contrastive on VGARank-Object | CoCa Base · VGARank-Object zero-shot | rank: 5.9 -> 5.8 | No clear effect |
| use generative retrieval with CoCa instead of TAP with in-domain pretraining | VAW · VAW SOTA comparison | overall mAP: 73.4 -> 72.0 | Hurt |
| use generative retrieval instead of SCoNE on rare attributes | VAW · VAW Tail mAP | mAP (%): 48.0 -> 60.6 | Improved |
Closest papers by meaning
- Revisiting the Role of Language Priors in Vision-Language Models (ICML 2024 · similarity 0.88)
- Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition (ICLR 2025 · similarity 0.88)
- Object Attribute Matters in Visual Question Answering (AAAI 2024 · similarity 0.88)
- EvdCLIP: Improving Vision-Language Retrieval with Entity Visual Descriptions from Large Language Models (AAAI 2025 · similarity 0.87)
- Tree of Attributes Prompt Learning for Vision-Language Models (ICLR 2025 · similarity 0.87)
- Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models (ICLR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
