Practical Insights into Semi-Supervised Object Detection Approaches
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912857158844416 |
|---|---|
| author | Wang, Chaoxin Balasubramaniyam, Bharaneeshwar Sangem, Anurag Guevara, Nicolais Caragea, Doina |
| author_facet | Wang, Chaoxin Balasubramaniyam, Bharaneeshwar Sangem, Anurag Guevara, Nicolais Caragea, Doina |
| contents | Learning in data-scarce settings has recently gained significant attention in the research community. Semi-supervised object detection(SSOD) aims to improve detection performance by leveraging a large number of unlabeled images alongside a limited number of labeled images(a.k.a.,few-shot learning). In this paper, we present a comprehensive comparison of three state-of-the-art SSOD approaches, including MixPL, Semi-DETR and Consistent-Teacher, with the goal of understanding how performance varies with the number of labeled images. We conduct experiments using the MS-COCO and Pascal VOC datasets, two popular object detection benchmarks which allow for standardized evaluation. In addition, we evaluate the SSOD approaches on a custom Beetle dataset which enables us to gain insights into their performance on specialized datasets with a smaller number of object categories. Our findings highlight the trade-offs between accuracy, model size, and latency, providing insights into which methods are best suited for low-data regimes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_13380 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Practical Insights into Semi-Supervised Object Detection Approaches Wang, Chaoxin Balasubramaniyam, Bharaneeshwar Sangem, Anurag Guevara, Nicolais Caragea, Doina Computer Vision and Pattern Recognition Learning in data-scarce settings has recently gained significant attention in the research community. Semi-supervised object detection(SSOD) aims to improve detection performance by leveraging a large number of unlabeled images alongside a limited number of labeled images(a.k.a.,few-shot learning). In this paper, we present a comprehensive comparison of three state-of-the-art SSOD approaches, including MixPL, Semi-DETR and Consistent-Teacher, with the goal of understanding how performance varies with the number of labeled images. We conduct experiments using the MS-COCO and Pascal VOC datasets, two popular object detection benchmarks which allow for standardized evaluation. In addition, we evaluate the SSOD approaches on a custom Beetle dataset which enables us to gain insights into their performance on specialized datasets with a smaller number of object categories. Our findings highlight the trade-offs between accuracy, model size, and latency, providing insights into which methods are best suited for low-data regimes. |
| title | Practical Insights into Semi-Supervised Object Detection Approaches |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.13380 |