Two-Level Attentions and Grouping Attention Convolutional Network for Fine-Grained Image Classification

Yang, Yadong; Wang, Xiaofeng; Zhao, Quan; Sui, Tingting

doi:10.3390/app9091939

Cited by 18 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While acquiring global features, the design generates special statistics-locationrelation descriptors to better describe the local features of parts and to generate special fine-grained part representation. In the overall structure, the hierachical CNN denoting skip-connections CNN (S-CCNN) [79] directly uses the feature maps of the first three levels of the convolutional layers and the last layer to combine and introduces a special module of "skip connection" for adjustment and classification. Two-level attentions and grouping attention CNN (TGA-CNN) [80] created a two-level attention model and a group attention model, which fuses the twostream features of pixel-level and object-level attention and merged the features with high similarity after channel feature processing to express the semantics better.…”

Section: Multi-stream Attentionmentioning

confidence: 99%

A survey of fine-grained visual categorization based on deep learning

Xie

Gong

Luan

et al. 2023

J. of Syst. Eng. Electron.

View full text Add to dashboard Cite

Deep learning has achieved excellent results in various tasks in the field of computer vision, especially in fine-grained visual categorization. It aims to distinguish the subordinate categories of the label-level categories. Due to high intra-class variances and high inter-class similarity, the fine-grained visual categorization is extremely challenging. This paper first briefly introduces and analyzes the related public datasets. After that, some of the latest methods are reviewed. Based on the feature types, the feature processing methods, and the overall structure used in the model, we divide them into three types of methods: methods based on general convolutional neural network (CNN) and strong supervision of parts, methods based on single feature processing, and methods based on multiple feature processing. Most methods of the first type have a relatively simple structure, which is the result of the initial research. The methods of the other two types include models that have special structures and training processes,which are helpful to obtain discriminative features. We conduct a specific analysis on several methods with high accuracy on public datasets. In addition, we support that the focus of the future research is to solve the demand of existing methods for the large amount of the data and the computing power. In terms of technology, the extraction of the subtle feature information with the burgeoning vision transformer (ViT) network is also an important research direction.

show abstract

Section: Multi-stream Attentionmentioning

confidence: 99%

A survey of fine-grained visual categorization based on deep learning

Xie

Gong

Luan

et al. 2023

J. of Syst. Eng. Electron.

View full text Add to dashboard Cite

show abstract

“…e attention mechanism is a deep learning technology that originated from the study of human vision and has been widely used in natural language processing [26,27], recommendation systems, and image classification [28,29]. It mimics the characteristics of the human visual system that selectively focuses on the salient parts, and improves the efficiency of the model by dynamically selecting important features.…”

Section: Attention Mechanismmentioning

confidence: 99%

A Novel Malware Detection and Family Classification Scheme for IoT Based on DEAM and DenseNet

Wang

Zhao

Wang

et al. 2021

Security and Communication Networks

View full text Add to dashboard Cite

With the rapid increase in the amount and type of malware, traditional methods of malware detection and family classification for IoT applications through static and dynamic analysis have been greatly challenged. In this paper, a new simple and effective attention module of Convolutional Neural Networks (CNNs), named as Depthwise Efficient Attention Module (DEAM), is proposed and combined with a DenseNet to propose a new malware detection and family classification model. Based on the good effect of the DenseNet in the field of image classification and the visual similarity of the malware family on images, the gray-scale image transformed from malware is input into the model combined with the DEAM and DenseNet for malware detection, and then the family classification is carried out. The DEAM is a general lightweight attention module improved based on the Convolutional Block Attention Module (CBAM), which can strengthen the attention to the characteristics of malware and improve the model effect. We use the MalImg dataset, Microsoft malware classification challenge dataset (BIG 2015), and our dataset constructed by the two above-mentioned datasets to verify the effectiveness of the proposed model in family classification and malware detection. Experimental results show that the proposed model achieves 99.3% in terms of accuracy for malware detection on our dataset and achieves 98.5% and 97.3% in terms of accuracy for family classification on the MalImg dataset and BIG 2015 dataset, respectively. The model can reliably detect IoT malware and classify its families.

show abstract

“…SCA-CNN [31] introduces spatial attention and channel attention into the convolutional structure and uses them in image annotation tasks. GA-CNN [32] obtains part-level attention by performing similarity clustering and grouping convolution on feature chan-nels. The channel attention and spatial attention mentioned above have been widely used in various image tasks and achieved good results.…”

Section: Related Work a Attention Convolutional Modelmentioning

confidence: 99%

Channel Expansion Convolutional Network for Image Classification

2020

Self Cite

View full text Add to dashboard Cite

With the continuous evolution of research on convolutional neural networks, it is an efficient and fashionable method to introduce attention mechanism into the convolutional structure. The channel attention designed in SENet has made a great contribution to the promotion of the attention convolution model. However, our research found that SENet focuses on certain feature channels rather than objects in the channels. It will simultaneously enhance or weaken the target objects and background information in a certain channel. On the basis of the channel attention convolution network, we first perform channel sorting and group convolution on the feature map, and expand each group to β times the original feature channel during the group convolution process to construct a channel expansion convolution network (CENet), where β is an array used to represent the channel expansion coefficient. CENet captures the attention of objects in the feature channel while expanding the proportion of features in the relatively important channel. Furthermore, we improved the structure of CENet and merged it into the intra-layer multi-scale convolutional model to construct an object-level attention multi-scale convolutional neural network (OAMS-CNN). We have conducted a large number of experiments on four data sets, CIFAR-10, CIFAR-100, FGVC-Aircraft and Stanford Cars. The experimental results show that our proposed new object-level attention convolution model has achieved good image classification results. INDEX TERMS Channel expansion network, object-level attention CNN, multi-scale CNN, image classification.

show abstract

Two-Level Attentions and Grouping Attention Convolutional Network for Fine-Grained Image Classification

Cited by 18 publications

References 44 publications

A survey of fine-grained visual categorization based on deep learning

A survey of fine-grained visual categorization based on deep learning

A Novel Malware Detection and Family Classification Scheme for IoT Based on DEAM and DenseNet

Channel Expansion Convolutional Network for Image Classification

Contact Info

Product

Resources

About