Semi-Supervised Object Detection
37 papers with code • 6 benchmarks • 1 datasets
Semi-supervised object detection uses both labeled data and unlabeled data for training. It not only reduces the annotation burden for training high-performance object detectors but also further improves the object detector by using a large number of unlabeled data.
This paper presents an end-to-end semi-supervised object detection approach, in contrast to previous more complex multi-stage methods.
Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data.
To address this, we introduce Unbiased Teacher, a simple yet effective approach that jointly trains a student and a gradually progressing teacher in a mutually-beneficial manner.
The Pseudo Label Assigner prevents the occurrence of bias caused by a large number of low-quality pseudo labels that may interfere with the Dense Detector during the student-teacher mutual learning mechanism, and the Epoch Adaptor utilizes domain and distribution adaptation to allow Dense Detector to learn globally distributed consistent features, making the training independent of the proportion of labeled data.
To remedy this issue, we present a novel label assignment mechanism for self-training framework, namely proposal self-assignment, which injects the proposals from student into teacher and generates accurate pseudo labels to match each proposal in the student model accordingly.
Specifically, we propose a Stage-wise Hybrid Matching strategy that combines the one-to-many assignment and one-to-one assignment strategies to improve the training efficiency of the first stage and thus provide high-quality pseudo labels for the training of the second stage.
To date, the most powerful semi-supervised object detectors (SS-OD) are based on pseudo-boxes, which need a sequence of post-processing with fine-tuned hyper-parameters.
(1) The teacher model serves a dual role as a teacher and a student, such that the teacher predictions on unlabeled images may be very close to those of student, which limits the upper-bound of the student.
To alleviate the confirmation bias problem and improve the quality of pseudo annotations, we further propose a co-rectify scheme based on Instant-Teaching, denoted as Instant-Teaching$^*$.