Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913595680358400 |
|---|---|
| author | Zhong, Xinhao Jiao, Siyu Zhao, Yao Wei, Yunchao |
| author_facet | Zhong, Xinhao Jiao, Siyu Zhao, Yao Wei, Yunchao |
| contents | Current Semi-Supervised Object Detection (SSOD) methods enhance detector performance by leveraging large amounts of unlabeled data, assuming that both labeled and unlabeled data share the same label space. However, in open-set scenarios, the unlabeled dataset contains both in-distribution (ID) classes and out-of-distribution (OOD) classes. Applying semi-supervised detectors in such settings can lead to misclassifying OOD class as ID classes. To alleviate this issue, we propose a simple yet effective method, termed Collaborative Feature-Logits Detector (CFL-Detector). Specifically, we introduce a feature-level clustering method using contrastive loss to clarify vector boundaries in the feature space and highlight class differences. Additionally, by optimizing the logits-level uncertainty classification loss, the model enhances its ability to effectively distinguish between ID and OOD classes. Extensive experiments demonstrate that our method achieves state-of-the-art performance compared to existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_13001 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection Zhong, Xinhao Jiao, Siyu Zhao, Yao Wei, Yunchao Computer Vision and Pattern Recognition Current Semi-Supervised Object Detection (SSOD) methods enhance detector performance by leveraging large amounts of unlabeled data, assuming that both labeled and unlabeled data share the same label space. However, in open-set scenarios, the unlabeled dataset contains both in-distribution (ID) classes and out-of-distribution (OOD) classes. Applying semi-supervised detectors in such settings can lead to misclassifying OOD class as ID classes. To alleviate this issue, we propose a simple yet effective method, termed Collaborative Feature-Logits Detector (CFL-Detector). Specifically, we introduce a feature-level clustering method using contrastive loss to clarify vector boundaries in the feature space and highlight class differences. Additionally, by optimizing the logits-level uncertainty classification loss, the model enhances its ability to effectively distinguish between ID and OOD classes. Extensive experiments demonstrate that our method achieves state-of-the-art performance compared to existing methods. |
| title | Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.13001 |