Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914939414773760 |
|---|---|
| author | Chhipa, Prakash Chandra De, Kanjar Chippa, Meenakshi Subhash Saini, Rajkumar Liwicki, Marcus |
| author_facet | Chhipa, Prakash Chandra De, Kanjar Chippa, Meenakshi Subhash Saini, Rajkumar Liwicki, Marcus |
| contents | The challenge of Out-Of-Distribution (OOD) robustness remains a critical hurdle towards deploying deep vision models. Vision-Language Models (VLMs) have recently achieved groundbreaking results. VLM-based open-vocabulary object detection extends the capabilities of traditional object detection frameworks, enabling the recognition and classification of objects beyond predefined categories. Investigating OOD robustness in recent open-vocabulary object detection is essential to increase the trustworthiness of these models. This study presents a comprehensive robustness evaluation of the zero-shot capabilities of three recent open-vocabulary (OV) foundation object detection models: OWL-ViT, YOLO World, and Grounding DINO. Experiments carried out on the robustness benchmarks COCO-O, COCO-DC, and COCO-C encompassing distribution shifts due to information loss, corruption, adversarial attacks, and geometrical deformation, highlighting the challenges of the model's robustness to foster the research for achieving robustness. Project page: https://prakashchhipa.github.io/projects/ovod_robustness |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_14874 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts Chhipa, Prakash Chandra De, Kanjar Chippa, Meenakshi Subhash Saini, Rajkumar Liwicki, Marcus Computer Vision and Pattern Recognition The challenge of Out-Of-Distribution (OOD) robustness remains a critical hurdle towards deploying deep vision models. Vision-Language Models (VLMs) have recently achieved groundbreaking results. VLM-based open-vocabulary object detection extends the capabilities of traditional object detection frameworks, enabling the recognition and classification of objects beyond predefined categories. Investigating OOD robustness in recent open-vocabulary object detection is essential to increase the trustworthiness of these models. This study presents a comprehensive robustness evaluation of the zero-shot capabilities of three recent open-vocabulary (OV) foundation object detection models: OWL-ViT, YOLO World, and Grounding DINO. Experiments carried out on the robustness benchmarks COCO-O, COCO-DC, and COCO-C encompassing distribution shifts due to information loss, corruption, adversarial attacks, and geometrical deformation, highlighting the challenges of the model's robustness to foster the research for achieving robustness. Project page: https://prakashchhipa.github.io/projects/ovod_robustness |
| title | Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.14874 |