# Proposal Learning for Semi-Supervised Object Detection Source: [Proposal Learning for Semi-Supervised Object Detection]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:15:13.389Z Authors: Peng Tang, Chetan Ramaiah, Yan Wang, Ran Xu, Caiming Xiong Published: 2020-01-15T00:06:59.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on MS-COCO additional](): Object Detection; MS-COCO additional; AP@\[.5:.95\]: 38.4. - [Object Detection on COCO (minival)](): Object Detection; COCO (minival); mAP: 38.4. - [Object Detection on COCO 2017 (val)](): Object Detection; COCO 2017 (val); AP: 38.4. - [Object Detection on MS-COCO 2017 (val)](): Object Detection; MS-COCO 2017 (val); mAP: not recorded. ## Original sources and implementation [Original paper]() [PDF]()