Proposal Learning for Semi-Supervised Object Detection

Abstract

In this paper, we focus on semi-supervised object detection to boost performance of proposal-based object detectors (a.k.a. two-stage object detectors) by training on both labeled and unlabeled data. However, it is non-trivial to train object detectors on unlabeled data due to the unavailability of ground truth labels. To address this problem, we present a proposal learning approach to learn proposal features and predictions from both labeled and unlabeled data. The approach consists of a self-supervised proposal learning module and a consistency-based proposal learning module. In the self-supervised proposal learning module, we present a proposal location loss and a contrastive loss to learn context-aware and noise-robust proposal features respectively. In the consistency-based proposal learning module, we apply consistency losses to both bounding box classification and regression predictions of proposals to learn noise-robust proposal features and predictions. Our approach enjoys the following benefits: 1) encouraging more context information to delivered in the proposals learning procedure; 2) noisy proposal features and enforcing consistency to allow noise-robust object detection; 3) building a general and high-performance semi-supervised object detection framework, which can be easily adapted to proposal-based object detectors with different backbone architectures. Experiments are conducted on the COCO dataset with all available labeled and unlabeled data. Results demonstrate that our approach consistently improves the performance of fully-supervised baselines. In particular, after combining with data distillation, our approach improves AP by about 2.0% and 0.9% on average compared to fully-supervised baselines and data distillation baselines respectively.

References in corpus (13)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• 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
• Momentum Contrast for Unsupervised Visual Representation Learning
• MMDetection: Open MMLab Detection Toolbox and Benchmark
• DropBlock: A regularization method for convolutional networks
• Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
• Deep High-Resolution Representation Learning for Visual Recognition
• LSDA: Large Scale Detection Through Adaptation
• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
• Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming

Cited by in corpus (6)

• A Simple Semi-Supervised Learning Framework for Object Detection
• Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework
• Points as Queries: Weakly Semi-supervised Object Detection by Points
• Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection
• Temporal Self-Ensembling Teacher for Semi-Supervised Object Detection
• Unsupervised Object Detection with LiDAR Clues