Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection

Abstract

In this paper, we delve into semi-supervised object detection where unlabeled images are leveraged to break through the upper bound of fully-supervised object detection models. Previous semi-supervised methods based on pseudo labels are severely degenerated by noise and prone to overfit to noisy labels, thus are deficient in learning different unlabeled knowledge well. To address this issue, we propose a data-uncertainty guided multi-phase learning method for semi-supervised object detection. We comprehensively consider divergent types of unlabeled images according to their difficulty levels, utilize them in different phases and ensemble models from different phases together to generate ultimate results. Image uncertainty guided easy data selection and region uncertainty guided RoI Re-weighting are involved in multi-phase learning and enable the detector to concentrate on more certain knowledge. Through extensive experiments on PASCAL VOC and MS COCO, we demonstrate that our method behaves extraordinarily compared to baseline approaches and outperforms them by a large margin, more than 3% on VOC and 2% on COCO.

arXiv commentAccepted by CVPR 2021

References in corpus (15)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• YOLOv3: An Incremental Improvement
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Unsupervised Data Augmentation for Consistency Training
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Temporal Ensembling for Semi-Supervised Learning
• Understanding deep learning requires rethinking generalization
• MMDetection: Open MMLab Detection Toolbox and Benchmark
• Weighted boxes fusion: Ensembling boxes from different object detection models
• The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
• Rethinking Pre-training and Self-training
• LSDA: Large Scale Detection Through Adaptation
• Soft Sampling for Robust Object Detection
• Interpolation-based semi-supervised learning for object detection
• Proposal Learning for Semi-Supervised Object Detection