YLYutong Lin

Yutong Lin

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yutong Lin has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Classification of Current Density Vector Maps for Heart Failures Using a Transfer Convolutional Neural Network

    by Zhenghui Hu, Yutong Lin, Kaikai Ye, Qiang Lin

    Ischemic heart disease (IHD) is the leading cause of death worldwide. Magnetocardiogram (MCG) as a non-invasive detection of the heart, takes a more important role in clinic detection. However, the MCG technique is not a common diagnostic tool in routine clinical practice because of the lack of MCG data and trained doctors for MCG data, especially for current density vector map (CDVM). Therefore, we propose an automatic method to analyze MCG data using the deep learning method. Here, we propose a deep learning method called Residual Network (ResNet) with transfer learning to classify CDVM from category 0 to category 4, which is reconstructed from MCG data. The ResNet exhibited an accuracy of 90.02%. This paper suggests a high potential for applying ResNet to CDVMs.


  • Open Access

    Swin Transformer V2: Scaling Up Capacity and Resolution

    by Ze Liu, Han Hu, Yutong Lin, Zhuliang Yao, Zhenda Xie, Yixuan Wei, Jia Ning, Yue Cao, Zheng Zhang, Li Dong, et al.

    Large-scale NLP models have been shown to significantly improve the performance on language tasks with no signs of saturation. They also demonstrate amazing few-shot capabilities like that of human beings. This paper aims to explore large-scale models in computer vision. We tackle three major issues in training and application of large vision models, including training instability, resolution gaps between pre-training and fine-tuning, and hunger on labelled data. Three main techniques are proposed: 1) a residual-post-norm method combined with cosine attention to improve training stability; 2) A log-spaced continuous position bias method to effectively transfer models pre-trained using low-resolution images to downstream tasks with high-resolution inputs; 3) A self-supervised pre-training method, SimMIM, to reduce the needs of vast labeled images. Through these techniques, this paper successfully trained a 3 billion-parameter Swin Transformer V2 model, which is the largest dense vision model to date, and makes it capable of training with images of up to 1,536$\times$1,536 resolution. It set new performance records on 4 representative vision tasks, including ImageNet-V2 image classification, COCO object detection, ADE20K semantic segmentation, and Kinetics-400 video action classification. Also note our training is much more efficient than that in Google's billion-level visual models, which consumes 40 times less labelled data and 40 times less training time. Code is available at \url{https://github.com/microsoft/Swin-Transformer}.


  • Open Access

    Self-Supervised Learning with Swin Transformers

    by Zhenda Xie, Yutong Lin, Zhuliang Yao, Zheng Zhang, Qi Dai, Yue Cao, Han Hu

    We are witnessing a modeling shift from CNN to Transformers in computer vision. In this work, we present a self-supervised learning approach called MoBY, with Vision Transformers as its backbone architecture. The approach basically has no new inventions, which is combined from MoCo v2 and BYOL and tuned to achieve reasonably high accuracy on ImageNet-1K linear evaluation: 72.8% and 75.0% top-1 accuracy using DeiT-S and Swin-T, respectively, by 300-epoch training. The performance is slightly better than recent works of MoCo v3 and DINO which adopt DeiT as the backbone, but with much lighter tricks. More importantly, the general-purpose Swin Transformer backbone enables us to also evaluate the learnt representations on downstream tasks such as object detection and semantic segmentation, in contrast to a few recent approaches built on ViT/DeiT which only report linear evaluation results on ImageNet-1K due to ViT/DeiT not tamed for these dense prediction tasks. We hope our results can facilitate more comprehensive evaluation of self-supervised learning methods designed for Transformer architectures. Our code and models are available at https://github.com/SwinTransformer/Transformer-SSL, which will be continually enriched.


  • Known-plaintext attack on JTC-based linear cryptosystem

    by Shuaifeng Dou, Xueju Shen, Bing Zhou, Chao Lin, Fuyu Huang, Yutong Lin


  • Security-enhanced nonlinear cryptosystem based on joint transform correlator

    by Shuaifeng Dou, Xueju Shen, Bing Zhou, Chao Lin, Yutong Lin, Yue Cheng