Yousong Zhu

Yousong Zhu

Auto-generated profile, based on publicly available information

Yousong Zhu

Chinese Academy of Sciences

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
13 August 2018 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
YZYousong Zhu
Yousong Zhu
CZChaoyang Zhao
Chaoyang Zhao
HGHaiyun Guo
Haiyun Guo
JWJinqiao Wang
Jinqiao Wang
XZXu Zhao
Xu Zhao
HLHanqing Lu
Hanqing Lu
The field of object detection has made great progress in recent years. Most of these improvements are derived from using a more sophisticated convolutional neural network. However, in the case of humans, the attention mechanism, global structure information, and local details of objects all play an important role for detecting an object. In this paper, we propose a novel fully convolutional network, named as Attention CoupleNet, to incorporate the attention-related information and global and local information of objects to improve the detection performance. Specifically, we first design a cascade attention structure to perceive the global scene of the image and generate class-agnostic attention maps. Then the attention maps are encoded into the network to acquire object-aware features. Next, we propose a unique fully convolutional coupling structure to couple global structure and local parts of the object to further formulate a discriminative feature representation. To fully explore the global and local properties, we also design different coupling strategies and normalization ways to make full use of the complementary advantages between the global and local information. Extensive experiments demonstrate the effectiveness of our approach. We achieve state-of-the-art results on all three challenging data sets, i.e., a mAP of 85.7% on VOC07, 84.3% on VOC12, and 35.4% on COCO. Codes are publicly available at https://github.com/tshizys/CoupleNet.

23 October 2022
Verified
Book Chapter
Closed access
PDF file
KZKuan Zhu
Kuan Zhu
HGhaiyun guo
haiyun guo
TYTianyi Yan
Tianyi Yan
YZYousong Zhu
Yousong Zhu
JWJinqiao Wang
Jinqiao Wang
MTMing Tang
Ming Tang

1 August 2020 in Neurocomputing
Verified
Journal Article
Closed access
SLSongyan Liu
Songyan Liu
HGHaiyun Guo
Haiyun Guo
JHJian-Guo Hu
Jian-Guo Hu
XZXu Zhao
Xu Zhao
CZChaoyang Zhao
Chaoyang Zhao
MTMing Tang
Ming Tang

2 October 2024
Verified
Book Chapter
Closed access
PDF file
YZYufei Zhan
Yufei Zhan
YZYousong Zhu
Yousong Zhu
ZCZhiyang Chen
Zhiyang Chen
FYFan Yang
Fan Yang
MTMing Tang
Ming Tang
JWJinqiao Wang
Jinqiao Wang

1 February 2020 in Neurocomputing
Verified
Journal Article
Closed access
YZYousong Zhu
Yousong Zhu
XZXu Zhao
Xu Zhao
CZChaoyang Zhao
Chaoyang Zhao
JWJinqiao Wang
Jinqiao Wang
HLHanqing Lu
Hanqing Lu

26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
YQYu Qi
Yu Qi
FYFan Yang
Fan Yang
YZYousong Zhu
Yousong Zhu
YLYufei Liu
Yufei Liu
LWLiwei Wu
Liwei Wu
WLWei Li
Wei Li
Autoregressive language modeling (ALM) has been successfully used in self-supervised pre-training in Natural language processing (NLP). However, this paradigm has not achieved comparable results with other self-supervised approaches in computer vision (e.g., contrastive learning, masked image modeling). In this paper, we try to find the reason why autoregressive modeling does not work well on vision tasks. To tackle this problem, we fully analyze the limitation of visual autoregressive methods and proposed a novel stochastic autoregressive image modeling (named SAIM) by the two simple designs. First, we serialize the image into patches. Second, we employ the stochastic permutation strategy to generate an effective and robust image context which is critical for vision tasks. To realize this task, we create a parallel encoder-decoder training process in which the encoder serves a similar role to the standard vision transformer focusing on learning the whole contextual information, and meanwhile the decoder predicts the content of the current position so that the encoder and decoder can reinforce each other. Our method significantly improves the performance of autoregressive image modeling and achieves the best accuracy (83.9%) on the vanilla ViT-Base model among methods using only ImageNet-1K data. Transfer performance in downstream tasks also shows that our model achieves competitive performance. Code is available at https://github.com/qiy20/SAIM.