Research map / Vision-language and multimodal / Human and embodied modeling
Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 multi-grained text-to-visual-concept pre-training | X-VLM · MSCOCO retrieval | text retrieval R@1: 75.4 -> 80.4 | Helped |
| Increase pre-training data from 4M to 16M images | X-VLM · MSCOCO retrieval | text retrieval R@1: 80.4 -> 81.2 | Helped |
| Increase pre-training data from 4M to 16M images | X-VLM · RefCOCO+ supervised | testA accuracy: 86.36 -> 89.00 | Helped |
| Add object concepts to pre-training (ablation) | X-VLM · MSCOCO retrieval | text retrieval R@1: 77.4 -> 78.8 | Helped |
| Add region concepts to pre-training (ablation) | X-VLM · MSCOCO retrieval | text retrieval R@1: 76.8 -> 78.8 | Helped |
| Add bounding-box prediction loss (ablation) | X-VLM · MSCOCO retrieval | text retrieval R@1: 77.5 -> 78.8 | Helped |
| Add object concepts, region concepts, and bounding-box prediction loss (ablation) | X-VLM · MSCOCO retrieval | text retrieval R@1: 74.5 -> 78.8 | Helped |
| Add object concepts to pre-training (ablation) | X-VLM · RefCOCO+ weakly supervised | testA accuracy: 73.37 -> 72.07 | Hurt |
| Add region concepts to pre-training (ablation) | X-VLM · RefCOCO+ weakly supervised | testA accuracy: 70.73 -> 72.07 | Helped |
| Add bounding-box prediction loss (ablation) | X-VLM · VQA | test-dev accuracy: 76.77 -> 76.20 | Hurt |
| Apply CIDEr optimization in the second fine-tuning stage | X-VLM (4M) · COCO Caption | CIDEr: 133.1 -> 140.8 | Helped |
Closest papers by meaning
- Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models (ICML 2024 · similarity 0.89)
- Synthesize Diagnose and Optimize: Towards Fine-Grained Vision-Language Understanding (CVPR 2024 · similarity 0.88)
- Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models (AAAI 2025 · similarity 0.88)
- Same or Not? Enhancing Visual Perception in Vision-Language Models (CVPR 2026 · similarity 0.88)
- Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models (ICML 2025 · similarity 0.88)
- Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation (ICLR 2026 · similarity 0.88)
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.