Person Reidentification by Multiscale Feature Representation Learning With Random Batch Feature Mask

Wu, Yong; Kun, Zhang; Wu, Di; Wang, Chao; Yuan, Changan; Qin, Xiao; Zhu, Tao; Du, Yuchuan; Wang, Han-Li; Huang, De-Shuang

doi:10.1109/tcds.2020.3003674

Cited by 47 publications

(11 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering that the constructed representation vector is high-dimensional and sparse, we hope to extract the effective features through Convolutional Neural Network (CNN) [ 48 – 50 ]. Compared to other machine learning method, CNN has its unique advantages in feature capture and model capacity [ 51 ].…”

Section: Methodsmentioning

confidence: 99%

A learning-based method to predict LncRNA-disease associations by combining CNN and ELM

et al. 2022

View full text Add to dashboard Cite

Background lncRNAs play a critical role in numerous biological processes and life activities, especially diseases. Considering that traditional wet experiments for identifying uncovered lncRNA-disease associations is limited in terms of time consumption and labor cost. It is imperative to construct reliable and efficient computational models as addition for practice. Deep learning technologies have been proved to make impressive contributions in many areas, but the feasibility of it in bioinformatics has not been adequately verified. Results In this paper, a machine learning-based model called LDACE was proposed to predict potential lncRNA-disease associations by combining Extreme Learning Machine (ELM) and Convolutional Neural Network (CNN). Specifically, the representation vectors are constructed by integrating multiple types of biology information including functional similarity and semantic similarity. Then, CNN is applied to mine both local and global features. Finally, ELM is chosen to carry out the prediction task to detect the potential lncRNA-disease associations. The proposed method achieved remarkable Area Under Receiver Operating Characteristic Curve of 0.9086 in Leave-one-out cross-validation and 0.8994 in fivefold cross-validation, respectively. In addition, 2 kinds of case studies based on lung cancer and endometrial cancer indicate the robustness and efficiency of LDACE even in a real environment. Conclusions Substantial results demonstrated that the proposed model is expected to be an auxiliary tool to guide and assist biomedical research, and the close integration of deep learning and biology big data will provide life sciences with novel insights.

show abstract

Section: Methodsmentioning

confidence: 99%

A learning-based method to predict LncRNA-disease associations by combining CNN and ELM

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Multi-scale Representations of CNN proved ample efficiency in many vision tasks including object detection [45], [46], semantic segmentation [47], [48], Re-ID [49] and image matching [50]. The multi-scale features extracted by versatile backbone like ResNet [18] and VGG [34] represent abundant detail and semantic information.…”

Section: Multi-scale Representations For Vision Tasksmentioning

confidence: 99%

CS-HSNet: A Cross-Siamese Change Detection Network Based on Hierarchical-Split Attention

Ke¹,

Zhang²

2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Change detection methods for optical remote sensing images play an important role in environmental resource management. Although recent methods based on deep learning demonstrate incredible ability by constructing networks: 1)Extracting bi-temporal features in a separate manner; 2)Fusing bi-temporal images before forwarding them into the single-level network. Both severely neglect the effect of spatial-temporal feature correlation between bi-temporal images. In addition, most existing methods represent multi-scale feature pairs in a layer-wise manner like ResNet, failing to consider the inner multi-level structure. In this work, we propose a new siamese change detection feature encoder backbone named Cross-Siamese Res2Net(CSRes2Net), by establishing crossed and hierarchical residual-like connections within one single residual block. The CSRes2Net represents dual features in a fine-grained manner and fully leads to the flow of bi-temporal features. In addition, recent learning-based methods designed some spatial-temporal relation modules to capture the pixel-level pairwise relationship and channel dependency based on self-attention mechanism, but they only consider spatial and channel dimension corrections separately with excessive parameters. So we propose a lightweight Cross Spatial-Channel Triplet Attention (CSCTA) module to capture cross-dimensional long-range relationship between triplet combinations: channel with height, channel with width, channel with channel. Finally, we propose a hierarchical-split block for generating multi-scale feature representations in a coarse-to-fine fashion. The experiments results on LEVIR-CD and Season-Varying Change Detection Data Set outperform most state-ofthe-art models.

show abstract

“…In recent years, due to the emergence of convolutional neural networks, deep learning has been applied more and more widely, including image recognition and natural language processing (Wu et al, 2018 ; Yuan et al, 2019 ; Qin et al, 2020 ; Wu Y. et al, 2020 ). Wu E. Q. et al ( 2019 ) proposed a Fuzzy Gaussian Support Vector Machine (FGSVM) as a top-level classification tool for deep learning models in order to more accurately classify the pilot's attention state images and analyze the abnormal conditions of the pilot's flight state.…”

Section: Introductionmentioning

confidence: 99%

Research and Application of Fine-Grained Image Classification Based on Small Collar Dataset

Huang

Yuan

Qin

2022

Front. Comput. Neurosci.

View full text Add to dashboard Cite

With the rapid development of apparel e-commerce, the variety of apparel is increasing, and it becomes more and more important to classify the apparel according to its collar design. Traditional image processing methods have been difficult to cope with the increasingly complex image backgrounds. To solve this problem, an EMRes-50 classification algorithm is proposed to solve the problem of garment collar image classification, which is designed based on the ECA-ResNet50 model combined with the MC-Loss loss function method. Applying the improved algorithm to the Coller-6 dataset, and the classification accuracy obtained was 73.6%. To further verify the effectiveness of the algorithm, it was applied to the DeepFashion-6 dataset, and the classification accuracy obtained was 86.09%. The experimental results show that the improved model has higher accuracy than the existing CNN model, and the model has better feature extraction ability, which is helpful to solve the problem of the difficulty of fine-grained collar classification and promote the further development of clothing product image classification.

show abstract

Person Reidentification by Multiscale Feature Representation Learning With Random Batch Feature Mask

Cited by 47 publications

References 49 publications

A learning-based method to predict LncRNA-disease associations by combining CNN and ELM

A learning-based method to predict LncRNA-disease associations by combining CNN and ELM

CS-HSNet: A Cross-Siamese Change Detection Network Based on Hierarchical-Split Attention

Research and Application of Fine-Grained Image Classification Based on Small Collar Dataset

Contact Info

Product

Resources

About