Towards End-to-end Semi-supervised Learning for One-stage Object Detection

by   Gen Luo, et al.

Semi-supervised object detection (SSOD) is a research hot spot in computer vision, which can greatly reduce the requirement for expensive bounding-box annotations. Despite great success, existing progress mainly focuses on two-stage detection networks like FasterRCNN, while the research on one-stage detectors is often ignored. In this paper, we focus on the semi-supervised learning for the advanced and popular one-stage detection network YOLOv5. Compared with Faster-RCNN, the implementation of YOLOv5 is much more complex, and the various training techniques used in YOLOv5 can also reduce the benefit of SSOD. In addition to this challenge, we also reveal two key issues in one-stage SSOD, which are low-quality pseudo-labeling and multi-task optimization conflict, respectively. To address these issues, we propose a novel teacher-student learning recipe called OneTeacher with two innovative designs, namely Multi-view Pseudo-label Refinement (MPR) and Decoupled Semi-supervised Optimization (DSO). In particular, MPR improves the quality of pseudo-labels via augmented-view refinement and global-view filtering, and DSO handles the joint optimization conflicts via structure tweaks and task-specific pseudo-labeling. In addition, we also carefully revise the implementation of YOLOv5 to maximize the benefits of SSOD, which is also shared with the existing SSOD methods for fair comparison. To validate OneTeacher, we conduct extensive experiments on COCO and Pascal VOC. The extensive experiments show that OneTeacher can not only achieve superior performance than the compared methods, e.g., 15.0 key issues in one-stage SSOD. Our source code is available at:


page 3

page 4

page 5

page 6

page 10

page 12


Active Teacher for Semi-Supervised Object Detection

In this paper, we study teacher-student learning from the perspective of...

Improving Localization for Semi-Supervised Object Detection

Nowadays, Semi-Supervised Object Detection (SSOD) is a hot topic, since,...

SOOD: Towards Semi-Supervised Oriented Object Detection

Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled dat...

Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection

Recent progress in weakly supervised object detection is featured by a c...

Fast and Efficient Model for Real-Time Tiger Detection In The Wild

The highest accuracy object detectors to date are based either on a two-...

Semi-DETR: Semi-Supervised Object Detection with Detection Transformers

We analyze the DETR-based framework on semi-supervised object detection ...

Pseudo-Labeling Enhanced by Privileged Information and Its Application to In Situ Sequencing Images

Various strategies for label-scarce object detection have been explored ...

Please sign up or login with your details

Forgot password? Click here to reset