paper-with-me

Papers

Diversified Multi-prototype Representation for Semi-supervised Segmentation

2021-11-16 · Jizong Peng, Christian Desrosiers, Marco Pedersoli

This work considers semi-supervised segmentation as a dense prediction problem based on prototype vector correlation and proposes a simple way to represent each segmentation class with multiple prototypes. To avoid degenerate solutions, two regularization strategies are applied on unlabeled images. The first one leverages mutual information maximization to ensure that all prototype vectors are considered by the network. The second explicitly enforces prototypes to be orthogonal by minimizing their cosine distance. Experimental results on two benchmark medical segmentation datasets reveal our method's effectiveness in improving segmentation performance when few annotated images are available.

📄 PDF Abstract BibTeX arXiv:2111.08651

Code (0)

등록된 구현이 없습니다.

Tasks

Segmentation

Similar Papers 제목 키워드 기반

Analyzing the Benefits of Prototypes for Semi-Supervised Category Learning

2024-06-04 · Liyi Zhang, Logan Nelson, Thomas L. Griffiths

Categories can be represented at different levels of abstraction, from prototypes focused on the most typical members to remembering all observed exemplars of the category. These representations have been explored in the…

Coded Residual Transform for Generalizable Deep Metric Learning

2022-10-09 · Shichao Kan, Yixiong Liang, Min Li, Yigang Cen 외

A fundamental challenge in deep metric learning is the generalization capability of the feature embedding network model since the embedding network learned on training classes need to be evaluated on new test classes. To…

Metric Learning

Open-world Semi-supervised Novel Class Discovery

2023-05-22 · Jiaming Liu, Yangqiming Wang, Tongze Zhang, Yulu Fan 외

Traditional semi-supervised learning tasks assume that both labeled and unlabeled data follow the same class distribution, but the realistic open-world scenarios are of more complexity with unknown novel classes mixed in…

Contrastive LearningNovel Class DiscoveryRepresentation Learning

Semi-supervised Domain Adaptation via Prototype-based Multi-level Learning

2023-05-04 · Xinyang Huang, Chuang Zhu, Wenkai Chen

In semi-supervised domain adaptation (SSDA), a few labeled target samples of each class help the model to transfer knowledge representation from the fully labeled source domain to the target domain. Many existing methods…

Domain AdaptationPseudo LabelSemi-supervised Domain AdaptationTransfer Learning

Multimodal Semi-Supervised Learning for 3D Objects

2021-10-22 · Zhimin Chen, Longlong Jing, Yang Liang, YingLi Tian 외

In recent years, semi-supervised learning has been widely explored and shows excellent data efficiency for 2D data. There is an emerging need to improve data efficiency for 3D tasks due to the scarcity of labeled 3D data…

3D ClassificationRetrieval