Yunhe Wang

Yunhe Wang

Auto-generated profile, based on publicly available information

Yunhe Wang

Huawei Noah's Ark Lab

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 February 2022 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
KHKai Han
Kai Han
YWYunhe Wang
Yunhe Wang
HCHanting Chen
Hanting Chen
XCXinghao Chen
Xinghao Chen
JGJianyuan Guo
Jianyuan Guo
DTDacheng Tao
Dacheng Tao
Transformer, first applied to the field of natural language processing, is a type of deep neural network mainly based on the self-attention mechanism. Thanks to its strong representation capabilities, researchers are looking at ways to apply transformer to computer vision tasks. In a variety of visual benchmarks, transformer-based models perform similar to or better than other types of networks such as convolutional and recurrent neural networks. Given its high performance and less need for vision-specific inductive bias, transformer is receiving more and more attention from the computer vision community. In this paper, we review these vision transformer models by categorizing them in different tasks and analyzing their advantages and disadvantages. The main categories we explore include the backbone network, high/mid-level vision, low-level vision, and video processing. We also include efficient transformer methods for pushing transformer into real device-based applications. Furthermore, we also take a brief look at the self-attention mechanism in computer vision, as it is the base component in transformer. Toward the end of this paper, we discuss the challenges and provide several further research directions for vision transformers.

2 March 2022 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
KHKai Han
Kai Han
YWYunhe Wang
Yunhe Wang
CXChang Xu
Chang Xu
JGJianyuan Guo
Jianyuan Guo
CXChunjing Xu
Chunjing Xu
QTQi Tian
Qi Tian

29 November 2024
Verified
Book Chapter
Closed access
PDF file
ZNZhenliang Ni
Zhenliang Ni
XCXinghao Chen
Xinghao Chen
YZYingjie Zhai
Yingjie Zhai
YTYehui Tang
Yehui Tang
YWYunhe Wang
Yunhe Wang

3 November 2022
Verified
Book Chapter
Closed access
PDF file
ZTZhijun Tu
Zhijun Tu
XCXinghao Chen
Xinghao Chen
PRPengju Ren
Pengju Ren
YWYunhe Wang
Yunhe Wang

19 July 2018 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YWYunhe Wang
Yunhe Wang
CXChang Xu
Chang Xu
CXChao Xu
Chao Xu
DTDacheng Tao
Dacheng Tao
Deep convolutional neural networks (CNNs) are successfully used in a number of applications. However, their storage and computational requirements have largely prevented their widespread use on mobile devices. Here we present a series of approaches for compressing and speeding up CNNs in the frequency domain, which focuses not only on smaller weights but on all the weights and their underlying connections. By treating convolution filters as images, we decompose their representations in the frequency domain as common parts (i.e., cluster centers) shared by other similar filters and their individual private parts (i.e., individual residuals). A large number of low-energy frequency coefficients in both parts can be discarded to produce high compression without significantly compression romising accuracy. Furthermore, we explore a data-driven method for removing redundancies in both spatial and frequency domains, which allows us to discard more useless weights by keeping similar accuracies. After obtaining the optimal sparse CNN in the frequency domain, we relax the computational burden of convolution operations in CNNs by linearly combining the convolution responses of discrete cosine transform (DCT) bases. The compression and speed-up ratios of the proposed algorithm are thoroughly analyzed and evaluated on benchmark image datasets to demonstrate its superiority over state-of-the-art methods.

23 October 2023 in arXiv
Verified
Preprint
Open access
PDF file
CWChengcheng Wang
Chengcheng Wang
WHWei He
Wei He
YNYing Nie
Ying Nie
JGJianyuan Guo
Jianyuan Guo
CLChuanjian Liu
Chuanjian Liu
YWYunhe Wang
Yunhe Wang
In the past years, YOLO-series models have emerged as the leading approaches in the area of real-time object detection. Many studies pushed up the baseline to a higher level by modifying the architecture, augmenting data and designing new losses. However, we find previous models still suffer from information fusion problem, although Feature Pyramid Network (FPN) and Path Aggregation Network (PANet) have alleviated this. Therefore, this study provides an advanced Gatherand-Distribute mechanism (GD) mechanism, which is realized with convolution and self-attention operations. This new designed model named as Gold-YOLO, which boosts the multi-scale feature fusion capabilities and achieves an ideal balance between latency and accuracy across all model scales. Additionally, we implement MAE-style pretraining in the YOLO-series for the first time, allowing YOLOseries models could be to benefit from unsupervised pretraining. Gold-YOLO-N attains an outstanding 39.9% AP on the COCO val2017 datasets and 1030 FPS on a T4 GPU, which outperforms the previous SOTA model YOLOv6-3.0-N with similar FPS by +2.4%. The PyTorch code is available at https://github.com/huawei-noah/Efficient-Computing/tree/master/Detection/Gold-YOLO, and the MindSpore code is available at https://gitee.com/mindspore/models/tree/master/research/cv/Gold_YOLO.