Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Wang, Renzhen"'
In online continual learning (CL), models trained on changing distributions easily forget previously learned knowledge and bias toward newly received tasks. To address this issue, we present Continual Bias Adaptor (CBA), a bi-level framework that aug
Externí odkaz:
http://arxiv.org/abs/2408.13991
Online continual learning (CL) aims to learn new knowledge and consolidate previously learned knowledge from non-stationary data streams. Due to the time-varying training setting, the model learned from a changing distribution easily forgets the prev
Externí odkaz:
http://arxiv.org/abs/2308.06925
Pseudo-labeling has proven to be a promising semi-supervised learning (SSL) paradigm. Existing pseudo-labeling methods commonly assume that the class distributions of training data are balanced. However, such an assumption is far from realistic scena
Externí odkaz:
http://arxiv.org/abs/2207.13856
Continual learning is a promising machine learning paradigm to learn new tasks while retaining previously learned knowledge over streaming training data. Till now, rehearsal-based methods, keeping a small part of data from old tasks as a memory buffe
Externí odkaz:
http://arxiv.org/abs/2112.15402
Hierarchical classification aims to sort the object into a hierarchical structure of categories. For example, a bird can be categorized according to a three-level hierarchy of order, family, and species. Existing methods commonly address hierarchical
Externí odkaz:
http://arxiv.org/abs/2112.02353
Autor:
Chen, Huai, Wang, Renzhen, Wang, Xiuying, Li, Jieyu, Fang, Qu, Li, Hui, Bai, Jianhao, Peng, Qing, Meng, Deyu, Wang, Lisheng
Contrastive learning, which aims to capture general representation from unlabeled images to initialize the medical analysis models, has been proven effective in alleviating the high demand for expensive annotations. Current methods mainly focus on in
Externí odkaz:
http://arxiv.org/abs/2108.09440
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. However, most existing methods encode the location informatio
Externí odkaz:
http://arxiv.org/abs/2106.14178
Autor:
Chen, Huai, Li, Jieyu, Wang, Renzhen, Huang, Yijie, Meng, Fanrui, Meng, Deyu, Peng, Qing, Wang, Lisheng
Local discriminative representation is needed in many medical image analysis tasks such as identifying sub-types of lesion or segmenting detailed components of anatomical structures. However, the commonly applied supervised representation learning me
Externí odkaz:
http://arxiv.org/abs/2012.09333
Deep neural networks often degrade significantly when training data suffer from class imbalance problems. Existing approaches, e.g., re-sampling and re-weighting, commonly address this issue by rearranging the label distribution of training data to t
Externí odkaz:
http://arxiv.org/abs/2008.03428
Autor:
Wang, Shuxin, Cao, Shilei, Wei, Dong, Wang, Renzhen, Ma, Kai, Wang, Liansheng, Meng, Deyu, Zheng, Yefeng
We introduce a one-shot segmentation method to alleviate the burden of manual annotation for medical images. The main idea is to treat one-shot segmentation as a classical atlas-based segmentation problem, where voxel-wise correspondence from the atl
Externí odkaz:
http://arxiv.org/abs/2003.07072