From Web Data to Real Fields: Low-Cost Unsupervised Domain Adaptation for Agricultural Robots
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909373737992192 |
|---|---|
| author | Tzouras, Vasileios Nalpantidis, Lazaros Güldenring, Ronja |
| author_facet | Tzouras, Vasileios Nalpantidis, Lazaros Güldenring, Ronja |
| contents | In precision agriculture, vision models often struggle with new, unseen fields where crops and weeds have been influenced by external factors, resulting in compositions and appearances that differ from the learned distribution. This paper aims to adapt to specific fields at low cost using Unsupervised Domain Adaptation (UDA). We explore a novel domain shift from a diverse, large pool of internet-sourced data to a small set of data collected by a robot at specific locations, minimizing the need for extensive on-field data collection. Additionally, we introduce a novel module -- the Multi-level Attention-based Adversarial Discriminator (MAAD) -- which can be integrated at the feature extractor level of any detection model. In this study, we incorporate MAAD with CenterNet to simultaneously detect leaf, stem, and vein instances. Our results show significant performance improvements in the unlabeled target domain compared to baseline models, with a 7.5% increase in object detection accuracy and a 5.1% improvement in keypoint detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_23906 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From Web Data to Real Fields: Low-Cost Unsupervised Domain Adaptation for Agricultural Robots Tzouras, Vasileios Nalpantidis, Lazaros Güldenring, Ronja Computer Vision and Pattern Recognition In precision agriculture, vision models often struggle with new, unseen fields where crops and weeds have been influenced by external factors, resulting in compositions and appearances that differ from the learned distribution. This paper aims to adapt to specific fields at low cost using Unsupervised Domain Adaptation (UDA). We explore a novel domain shift from a diverse, large pool of internet-sourced data to a small set of data collected by a robot at specific locations, minimizing the need for extensive on-field data collection. Additionally, we introduce a novel module -- the Multi-level Attention-based Adversarial Discriminator (MAAD) -- which can be integrated at the feature extractor level of any detection model. In this study, we incorporate MAAD with CenterNet to simultaneously detect leaf, stem, and vein instances. Our results show significant performance improvements in the unlabeled target domain compared to baseline models, with a 7.5% increase in object detection accuracy and a 5.1% improvement in keypoint detection. |
| title | From Web Data to Real Fields: Low-Cost Unsupervised Domain Adaptation for Agricultural Robots |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.23906 |