Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.07089 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916997323816960 |
|---|---|
| author | Gonzalez, Federico Talavera, Estefania Radeva, Petia |
| author_facet | Gonzalez, Federico Talavera, Estefania Radeva, Petia |
| contents | Unsupervised object discovery, the task of identifying and localizing objects in images without human-annotated labels, remains a significant challenge and a growing focus in computer vision. In this work, we introduce a novel model, DADO (Depth-Attention self-supervised technique for Discovering unseen Objects), which combines an attention mechanism and a depth model to identify potential objects in images. To address challenges such as noisy attention maps or complex scenes with varying depth planes, DADO employs dynamic weighting to adaptively emphasize attention or depth features based on the global characteristics of each image. We evaluated DADO on standard benchmarks, where it outperforms state-of-the-art methods in object discovery accuracy and robustness without the need for fine-tuning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07089 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DADO: A Depth-Attention framework for Object Discovery Gonzalez, Federico Talavera, Estefania Radeva, Petia Computer Vision and Pattern Recognition Unsupervised object discovery, the task of identifying and localizing objects in images without human-annotated labels, remains a significant challenge and a growing focus in computer vision. In this work, we introduce a novel model, DADO (Depth-Attention self-supervised technique for Discovering unseen Objects), which combines an attention mechanism and a depth model to identify potential objects in images. To address challenges such as noisy attention maps or complex scenes with varying depth planes, DADO employs dynamic weighting to adaptively emphasize attention or depth features based on the global characteristics of each image. We evaluated DADO on standard benchmarks, where it outperforms state-of-the-art methods in object discovery accuracy and robustness without the need for fine-tuning. |
| title | DADO: A Depth-Attention framework for Object Discovery |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.07089 |