Semi-supervised Object Detection via Virtual Category Learning
Due to the costliness of labelled data in real-world applications, semi-supervised object detectors, underpinned by pseudo labelling, are appealing. However, handling confusing samples is nontrivial: discarding valuable confusing samples would compromise the model generalisation while using them for training would exacerbate the confirmation bias issue caused by inevitable mislabelling. To solve this problem, this paper proposes to use confusing samples proactively without label correction. Specifically, a virtual category (VC) is assigned to each confusing sample such that they can safely contribute to the model optimisation even without a concrete label. It is attributed to specifying the embedding distance between the training sample and the virtual category as the lower bound of the inter-class distance. Moreover, we also modify the localisation loss to allow high-quality boundaries for location regression. Extensive experiments demonstrate that the proposed VC learning significantly surpasses the state-of-the-art, especially with small amounts of available labels.
Code (1)
Tasks
Objectobject-detectionObject DetectionSemi-Supervised Object DetectionSimilar Papers 제목 키워드 기반
Semi-supervised Object Detection via Virtual Category Learning
Due to the lack of large amounts of labelled data to learn rich-expressive features of objects, semi-supervised detectors powered by pseudo labelling techniques usually make a tentative decision for the pseudo labels of …
Objectobject-detectionObject DetectionSemi-Supervised Object DetectionVirtual Category Learning: A Semi-Supervised Learning Method for Dense Prediction with Extremely Limited Labels
Due to the costliness of labelled data in real-world applications, semi-supervised learning, underpinned by pseudo labelling, is an appealing solution. However, handling confusing samples is nontrivial: discarding valuab…
object-detectionObject DetectionSemantic SegmentationClass-balanced Open-set Semi-supervised Object Detection for Medical Images
Medical image datasets in the real world are often unlabeled and imbalanced, and Semi-Supervised Object Detection (SSOD) can utilize unlabeled data to improve an object detector. However, existing approaches predominantl…
Objectobject-detectionObject DetectionOut-of-Distribution Detection+1Power of Cooperative Supervision: Multiple Teachers Framework for Enhanced 3D Semi-Supervised Object Detection
To ensure safe urban driving for autonomous platforms, it is crucial not only to develop high-performance object detection techniques but also to establish a diverse and representative dataset that captures various urban…
Objectobject-detectionObject DetectionSemi-Supervised Object DetectionVideo Object Segmentation using Tracked Object Proposals
We present an approach to semi-supervised video object segmentation, in the context of the DAVIS 2017 challenge. Our approach combines category-based object detection, category-independent object appearance segmentation …
Objectobject-detectionObject DetectionObject Tracking+5