Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2411.05564 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929583778955264 |
|---|---|
| author | Ammar, Hejer Kiselov, Nikita Lapouge, Guillaume Audigier, Romaric |
| author_facet | Ammar, Hejer Kiselov, Nikita Lapouge, Guillaume Audigier, Romaric |
| contents | In real-world applications where confidence is key, like autonomous driving, the accurate detection and appropriate handling of classes differing from those used during training are crucial. Despite the proposal of various unknown object detection approaches, we have observed widespread inconsistencies among them regarding the datasets, metrics, and scenarios used, alongside a notable absence of a clear definition for unknown objects, which hampers meaningful evaluation. To counter these issues, we introduce two benchmarks: a unified VOC-COCO evaluation, and the new OpenImagesRoad benchmark which provides clear hierarchical object definition besides new evaluation metrics. Complementing the benchmark, we exploit recent self-supervised Vision Transformers performance, to improve pseudo-labeling-based OpenSet Object Detection (OSOD), through OW-DETR++. State-of-the-art methods are extensively evaluated on the proposed benchmarks. This study provides a clear problem definition, ensures consistent evaluations, and draws new conclusions about effectiveness of OSOD strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_05564 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Open-set object detection: towards unified problem formulation and benchmarking Ammar, Hejer Kiselov, Nikita Lapouge, Guillaume Audigier, Romaric Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning In real-world applications where confidence is key, like autonomous driving, the accurate detection and appropriate handling of classes differing from those used during training are crucial. Despite the proposal of various unknown object detection approaches, we have observed widespread inconsistencies among them regarding the datasets, metrics, and scenarios used, alongside a notable absence of a clear definition for unknown objects, which hampers meaningful evaluation. To counter these issues, we introduce two benchmarks: a unified VOC-COCO evaluation, and the new OpenImagesRoad benchmark which provides clear hierarchical object definition besides new evaluation metrics. Complementing the benchmark, we exploit recent self-supervised Vision Transformers performance, to improve pseudo-labeling-based OpenSet Object Detection (OSOD), through OW-DETR++. State-of-the-art methods are extensively evaluated on the proposed benchmarks. This study provides a clear problem definition, ensures consistent evaluations, and draws new conclusions about effectiveness of OSOD strategies. |
| title | Open-set object detection: towards unified problem formulation and benchmarking |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2411.05564 |