Collaboration of Teachers for Semi-supervised Object Detection

TL;DR

This paper introduces a collaborative teacher-student framework for semi-supervised object detection that enhances unlabeled data utilization and reduces confirmation bias, leading to improved accuracy and faster convergence.

Contribution

The proposed Collaboration of Teachers Framework (CTF) uses multiple teacher-student pairs and a data performance consistency module to select optimal pseudo-labels, advancing SSOD methods.

Findings

Achieves 0.71% mAP improvement on COCO with 10% labels

Achieves 0.89% mAP improvement on VOC dataset

Converges faster than existing methods

Abstract

Recent semi-supervised object detection (SSOD) has achieved remarkable progress by leveraging unlabeled data for training. Mainstream SSOD methods rely on Consistency Regularization methods and Exponential Moving Average (EMA), which form a cyclic data flow. However, the EMA updating training approach leads to weight coupling between the teacher and student models. This coupling in a cyclic data flow results in a decrease in the utilization of unlabeled data information and the confirmation bias on low-quality or erroneous pseudo-labels. To address these issues, we propose the Collaboration of Teachers Framework (CTF), which consists of multiple pairs of teacher and student models for training. In the learning process of CTF, the Data Performance Consistency Optimization module (DPCO) informs the best pair of teacher models possessing the optimal pseudo-labels during the past training process, and these most reliable pseudo-labels generated by the best performing teacher would guide the other student models. As a consequence, this framework greatly improves the utilization of unlabeled data and prevents the positive feedback cycle of unreliable pseudo-labels. The CTF achieves outstanding results on numerous SSOD datasets, including a 0.71% mAP improvement on the 10% annotated COCO dataset and a 0.89% mAP improvement on the VOC dataset compared to LabelMatch and converges significantly faster. Moreover, the CTF is plug-and-play and can be integrated with other mainstream SSOD methods.