VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916664825610240 |
|---|---|
| author | Zhang, Bin Qu, Xiaoyang Li, Guokuan Wan, Jiguang Wang, Jianzong |
| author_facet | Zhang, Bin Qu, Xiaoyang Li, Guokuan Wan, Jiguang Wang, Jianzong |
| contents | As object detectors are increasingly deployed as black-box cloud services or pre-trained models with restricted access to the original training data, the challenge of zero-shot object-level out-of-distribution (OOD) detection arises. This task becomes crucial in ensuring the reliability of detectors in open-world settings. While existing methods have demonstrated success in image-level OOD detection using pre-trained vision-language models like CLIP, directly applying such models to object-level OOD detection presents challenges due to the loss of contextual information and reliance on image-level alignment. To tackle these challenges, we introduce a new method that leverages visual prompts and text-augmented in-distribution (ID) space construction to adapt CLIP for zero-shot object-level OOD detection. Our method preserves critical contextual information and improves the ability to differentiate between ID and OOD objects, achieving competitive performance across different benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_22291 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection Zhang, Bin Qu, Xiaoyang Li, Guokuan Wan, Jiguang Wang, Jianzong Computer Vision and Pattern Recognition As object detectors are increasingly deployed as black-box cloud services or pre-trained models with restricted access to the original training data, the challenge of zero-shot object-level out-of-distribution (OOD) detection arises. This task becomes crucial in ensuring the reliability of detectors in open-world settings. While existing methods have demonstrated success in image-level OOD detection using pre-trained vision-language models like CLIP, directly applying such models to object-level OOD detection presents challenges due to the loss of contextual information and reliance on image-level alignment. To tackle these challenges, we introduce a new method that leverages visual prompts and text-augmented in-distribution (ID) space construction to adapt CLIP for zero-shot object-level OOD detection. Our method preserves critical contextual information and improves the ability to differentiate between ID and OOD objects, achieving competitive performance across different benchmarks. |
| title | VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.22291 |