Search Results for author: Renzhen Wang

Found 7 papers, 2 papers with code

Revisiting Experience Replay: Continual Learning by Adaptively Tuning Task-wise Relationship

no code implementations31 Dec 2021 Quanziang Wang, Yuexiang Li, Dong Wei, Renzhen Wang, Kai Ma, Yefeng Zheng, Deyu Meng

These approaches save a small part of the data of the past tasks as a memory buffer to prevent models from forgetting previously learned knowledge.

Continual Learning Meta-Learning

Label Hierarchy Transition: Modeling Class Hierarchies to Enhance Deep Classifiers

no code implementations4 Dec 2021 Renzhen Wang, De Cai, Kaiwen Xiao, Xixi Jia, Xiao Han, Deyu Meng

In this paper, we propose Label Hierarchy Transition, a unified probabilistic framework based on deep learning, to address hierarchical classification.

Classification Multi-class Classification +1

Unsupervised Local Discrimination for Medical Images

1 code implementation21 Aug 2021 Huai Chen, Renzhen Wang, Jieyu Li, Jianhao Bai, Qing Peng, Deyu Meng, Lisheng Wang

Following the fact that images of the same body region should share similar anatomical structures, and pixels of the same structure should have similar semantic patterns, we design a neural network to construct a local discriminative embedding space where pixels with similar contexts are clustered and dissimilar pixels are dispersed.

Contrastive Learning Representation Learning

Residual Moment Loss for Medical Image Segmentation

no code implementations27 Jun 2021 Quanziang Wang, Renzhen Wang, Yuexiang Li, Kai Ma, Yefeng Zheng, Deyu Meng

Location information is proven to benefit the deep learning models on capturing the manifold structure of target objects, and accordingly boosts the accuracy of medical image segmentation.

Medical Image Segmentation Semantic Segmentation

Unsupervised Learning of Local Discriminative Representation for Medical Images

1 code implementation17 Dec 2020 Huai Chen, Jieyu Li, Renzhen Wang, YiJie Huang, Fanrui Meng, Deyu Meng, Qing Peng, Lisheng Wang

However, the commonly applied supervised representation learning methods require a large amount of annotated data, and unsupervised discriminative representation learning distinguishes different images by learning a global feature, both of which are not suitable for localized medical image analysis tasks.

Representation Learning

Meta Feature Modulator for Long-tailed Recognition

no code implementations8 Aug 2020 Renzhen Wang, Kaiqin Hu, Yanwen Zhu, Jun Shu, Qian Zhao, Deyu Meng

We further design a modulator network to guide the generation of the modulation parameters, and such a meta-learner can be readily adapted to train the classification network on other long-tailed datasets.

General Classification Meta-Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.