Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.04270 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908634850525184 |
|---|---|
| author | Choi, Sangbum Go, Kyeongryeol Jang, Taewoong |
| author_facet | Choi, Sangbum Go, Kyeongryeol Jang, Taewoong |
| contents | Foundation models have revolutionized AI, yet they struggle with zero-shot deployment in real-world industrial settings due to a lack of high-quality, domain-specific datasets. To bridge this gap, Superb AI introduces ZERO, an industry-ready vision foundation model that leverages multi-modal prompting (textual and visual) for generalization without retraining. Trained on a compact yet representative 0.9 million annotated samples from a proprietary billion-scale industrial dataset, ZERO demonstrates competitive performance on academic benchmarks like LVIS-Val and significantly outperforms existing models across 37 diverse industrial datasets. Furthermore, ZERO achieved 2nd place in the CVPR 2025 Object Instance Detection Challenge and 4th place in the Foundational Few-shot Object Detection Challenge, highlighting its practical deployability and generalizability with minimal adaptation and limited data. To the best of our knowledge, ZERO is the first vision foundation model explicitly built for domain-specific, zero-shot industrial applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04270 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ZERO: Industry-ready Vision Foundation Model with Multi-modal Prompts Choi, Sangbum Go, Kyeongryeol Jang, Taewoong Computer Vision and Pattern Recognition Artificial Intelligence Foundation models have revolutionized AI, yet they struggle with zero-shot deployment in real-world industrial settings due to a lack of high-quality, domain-specific datasets. To bridge this gap, Superb AI introduces ZERO, an industry-ready vision foundation model that leverages multi-modal prompting (textual and visual) for generalization without retraining. Trained on a compact yet representative 0.9 million annotated samples from a proprietary billion-scale industrial dataset, ZERO demonstrates competitive performance on academic benchmarks like LVIS-Val and significantly outperforms existing models across 37 diverse industrial datasets. Furthermore, ZERO achieved 2nd place in the CVPR 2025 Object Instance Detection Challenge and 4th place in the Foundational Few-shot Object Detection Challenge, highlighting its practical deployability and generalizability with minimal adaptation and limited data. To the best of our knowledge, ZERO is the first vision foundation model explicitly built for domain-specific, zero-shot industrial applications. |
| title | ZERO: Industry-ready Vision Foundation Model with Multi-modal Prompts |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2507.04270 |