paper-with-me

홈 › Papers

Virtual Category Learning: A Semi-Supervised Learning Method for Dense Prediction with Extremely Limited Labels

2023-12-02 · Changrui Chen, Jungong Han, Kurt Debattista

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 valuable confusing samples would compromise the model generalisation while using them for training would exacerbate the issue of confirmation bias caused by the resulting 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 in such a way that it can safely contribute to the model optimisation even without a concrete label. This provides an upper bound for inter-class information sharing capacity, which eventually leads to a better embedding space. Extensive experiments on two mainstream dense prediction tasks -- semantic segmentation and object detection, demonstrate that the proposed VC learning significantly surpasses the state-of-the-art, especially when only very few labels are available. Our intriguing findings highlight the usage of VC learning in dense vision tasks.

📄 PDF Abstract BibTeX arXiv:2312.01169

Code (1)

geoffreychen777/vc 공식 구현 pytorch

Tasks

object-detectionObject DetectionSemantic Segmentation

Similar Papers 제목 키워드 기반

Semi-supervised Object Detection via Virtual Category Learning

2022-07-07 · Changrui Chen, Kurt Debattista, Jungong Han

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 …

Objectobject-detectionObject DetectionSemi-Supervised Object Detection

Semi-supervised Object Detection via Virtual Category Learning

2021-11-25 · Anonymous

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 Detection

LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature Similarity

2022-04-06 · Tejan Karmali, Abhinav Atrishi, Sai Sree Harsha, Susmit Agrawal 외

In this work, we introduce LEAD, an approach to discover landmarks from an unannotated collection of category-specific images. Existing works in self-supervised landmark detection are based on learning dense (pixel-level…

Self-Supervised Learning

Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks

2022-10-18 · Miquel Martí i Rabadán, Alessandro Pieropan, Hossein Azizpour, Atsuto Maki

We propose Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks combining pseudo-labeling and consistency regularization via strong data augmentation. We enable the…

Data Augmentationimage-classificationSemantic SegmentationSemi-Supervised Semantic Segmentation

Virtual Adversarial Training on Graph Convolutional Networks in Node Classification

2019-02-28 · Ke Sun, Zhouchen Lin, Hantao Guo, Zhanxing Zhu

The effectiveness of Graph Convolutional Networks (GCNs) has been demonstrated in a wide range of graph-based machine learning tasks. However, the update of parameters in GCNs is only from labeled nodes, lacking the util…

ClassificationGeneral ClassificationNode Classification