Zhenyi Zhang

Zhenyi Zhang

Auto-generated profile, based on publicly available information

Zhenyi Zhang

School of Physics and Electronics, Shandong Normal University, Jinan, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
15 April 2024 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
TLTianping Li
Tianping Li
ZZZhenyi Zhang
Zhenyi Zhang
MZMengdi Zhu
Mengdi Zhu
ZCZhaotong Cui
Zhaotong Cui
DWDongmei Wei
Dongmei Wei
Convolutional neural network (CNN)-based object detectors perform excellently but lack global feature extraction and cannot establish global dependencies between object pixels. Although the Transformer is able to compensate for this, it does not incorporate the advantages of convolution, which results in insufficient information being obtained about the details of local features, as well as slow speed and large computational parameters. In addition, Feature Pyramid Network (FPN) lacks information interaction across layers, which can reduce the acquisition of feature context information. To solve the above problems, this paper proposes a CNN-based anchor-free object detector that combines transformer global and local feature extraction (GLFT) to enhance the extraction of semantic information from images. First, the segmented channel extraction feature attention (SCEFA) module was designed to improve the extraction of local multiscale channel features from the model and enhance the discrimination of pixels in the object region. Second, the aggregated feature hybrid transformer (AFHTrans) module combined with convolution is designed to enhance the extraction of global and local feature information from the model and to establish the dependency of the pixels of distant objects. This approach compensates for the shortcomings of the FPN by means of multilayer information aggregation transmission. Compared with a transformer, these methods have obvious advantages. Finally, the feature extraction head (FE-Head) was designed to extract full-text information based on the features of different tasks. An accuracy of 47.0% and 82.76% was achieved on the COCO2017 and PASCAL VOC2007 + 2012 datasets, respectively, and the experimental results validate the effectiveness of our method.

14 November 2024 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
TLTianping Li
Tianping Li
XYXiaolong Yang
Xiaolong Yang
ZZZhenyi Zhang
Zhenyi Zhang
ZCZhaotong Cui
Zhaotong Cui
MZMaoxia Zhou
Maoxia Zhou
Recently, a number of vision transformer models for semantic segmentation have been proposed, with the majority of these achieving impressive results. However, they lack the ability to exploit the intrinsic position and channel features of the image and are less capable of multi-scale feature fusion. This paper presents a semantic segmentation method that successfully combines attention and multiscale representation, thereby enhancing performance and efficiency. This represents a significant advancement in the field. Multi-layers semantic extraction and multi-scale aggregation transformer decoder (MEMAFormer) is proposed, which consists of two components: mix-layers dual channel semantic extraction module (MDCE) and semantic aggregation pyramid pooling module (SAPPM). The MDCE incorporates a multi-layers cross attention module (MCAM) and an efficient channel attention module (ECAM). In MCAM, horizontal connections between encoder and decoder stages are employed as feature queries for the attention module. The hierarchical feature maps derived from different encoder and decoder stages are integrated into key and value. To address long-term dependencies, ECAM selectively emphasizes interdependent channel feature maps by integrating relevant features across all channels. The adaptability of the feature maps is reduced by pyramid pooling, which reduces the amount of computation without compromising performance. SAPPM is comprised of several distinct pooled kernels that extract context with a deeper flow of information, forming a multi-scale feature by integrating various feature sizes. The MEMAFormer-B0 model demonstrates superior performance compared to SegFormer-B0, exhibiting gains of 4.8%, 4.0% and 3.5% on the ADE20K, Cityscapes and COCO-stuff datasets, respectively.

21 March 2024
Verified
Book Chapter
Open access
PDF file
ZZZhenyi Zhang
Zhenyi Zhang
TLTianping Li
Tianping Li
Numerous fields, including autonomous driving, facial recognition, video monitoring, and medical picture analysis, use object detection. The Task-aligned One-stage Object Detection (TOOD) technique, however, will result in information loss and slow detection speeds when classifying and aligning objects. In order to increase the receptive field of detection and lower the amount of calculations required by the model, a Receptive Field Enhancement Module (RFEM) is added between the backbone network and the neck network of the detector in this article. This effectively addresses the issues of decreasing accuracy and slow speed. Then, in the head network, the original detecting head is switched out for an Enhanced Task Alignment Head (ET-Head) based on Layer Hybrid Attention Module (LHAM), which significantly enhances the detector's performance and feature extraction capability. Additionally, SIOU loss is used in place of regression loss to enhance the training effect. For our experiments, we use the PASCAL VOC dataset. According to experimental findings, the detection accuracy is up 1.1% compared to the TOOD algorithm, and the speed is up 1 frame per second (FPS).