Few-Shot Object Detection with Sparse Context Transformers
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910331353169920 |
|---|---|
| author | Mei, Jie Jiu, Mingyuan Sahbi, Hichem Jiang, Xiaoheng Xu, Mingliang |
| author_facet | Mei, Jie Jiu, Mingyuan Sahbi, Hichem Jiang, Xiaoheng Xu, Mingliang |
| contents | Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data. One of the mainstream few-shot methods is transfer learning which consists in pretraining a detection model in a source domain prior to its fine-tuning in a target domain. However, it is challenging for fine-tuned models to effectively identify new classes in the target domain, particularly when the underlying labeled training data are scarce. In this paper, we devise a novel sparse context transformer (SCT) that effectively leverages object knowledge in the source domain, and automatically learns a sparse context from only few training images in the target domain. As a result, it combines different relevant clues in order to enhance the discrimination power of the learned detectors and reduce class confusion. We evaluate the proposed method on two challenging few-shot object detection benchmarks, and empirical results show that the proposed method obtains competitive performance compared to the related state-of-the-art. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09315 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Few-Shot Object Detection with Sparse Context Transformers Mei, Jie Jiu, Mingyuan Sahbi, Hichem Jiang, Xiaoheng Xu, Mingliang Computer Vision and Pattern Recognition Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data. One of the mainstream few-shot methods is transfer learning which consists in pretraining a detection model in a source domain prior to its fine-tuning in a target domain. However, it is challenging for fine-tuned models to effectively identify new classes in the target domain, particularly when the underlying labeled training data are scarce. In this paper, we devise a novel sparse context transformer (SCT) that effectively leverages object knowledge in the source domain, and automatically learns a sparse context from only few training images in the target domain. As a result, it combines different relevant clues in order to enhance the discrimination power of the learned detectors and reduce class confusion. We evaluate the proposed method on two challenging few-shot object detection benchmarks, and empirical results show that the proposed method obtains competitive performance compared to the related state-of-the-art. |
| title | Few-Shot Object Detection with Sparse Context Transformers |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.09315 |