Research map / Vision-language and multimodal / Human and embodied modeling
OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning
Sheng Liu, Kevin Lin, Lijuan Wang, Junsong Yuan, Zicheng Liu
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 ViSA instead of Det+DeViSE | OVIS visual instance search · OVIS40-small | mAP_all: 5.4 -> 34.8 | Improved |
| Use ViSA instead of Det+DeViSE | OVIS visual instance search · OVIS40-medium | mAP_all: 4.7 -> 30.6 | Improved |
| Use ViSA instead of Det+DeViSE | OVIS visual instance search · OVIS40-large | mAP_all: 3.0 -> 21.9 | Improved |
| Use ViSA instead of Det+DeViSE | OVIS visual instance search · OVIS1600 | mAP_all: 2.2 -> 14.9 | Improved |
| Add visual instance label prediction (ILP) to masked token prediction (MTP) (ablation) | ViSA · OVIS40-medium | mAP_all: 24.0 -> 30.6 | Improved |
| Add visual instance label prediction (ILP) to masked token prediction (MTP) (ablation) | ViSA · OVIS40-large | mAP_all: 19.2 -> 21.9 | Improved |
| Use ILP without masked token prediction (MTP) (ablation) | ViSA · OVIS40-medium | mAP_all: 24.0 -> 0.0 | Hurt |
| Use ILP without masked token prediction (MTP) (ablation) | ViSA · OVIS40-large | mAP_all: 19.2 -> 0.0 | Hurt |
| Replace dot product similarity with cosine similarity (ablation) | ViSA · OVIS40-small | mAP_all: 34.8 -> 32.8 | No clear effect |
| Replace dot product similarity with cosine similarity (ablation) | ViSA · OVIS40-medium | mAP_all: 30.6 -> 30.0 | No clear effect |
| Replace dot product similarity with cosine similarity (ablation) | ViSA · OVIS40-large | mAP_all: 21.9 -> 19.5 | No clear effect |
Closest papers by meaning
- Beyond Instance-Level Image Retrieval: Leveraging Captions to Learn a Global Visual Representation for Semantic Retrieval (CVPR 2017 · similarity 0.90)
- Image-Text Embedding Learning via Visual and Textual Semantic Reasoning (TPAMI 2022 · similarity 0.88)
- Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models (CVPR 2024 · similarity 0.87)
- Instance-Level Composed Image Retrieval (NeurIPS 2025 · similarity 0.87)
- Asymmetric Visual Semantic Embedding Framework for Efficient Vision-Language Alignment (AAAI 2025 · similarity 0.87)
- Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models (ICML 2024 · 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.
