The application of two-level attention models in deep convolutional neural network for fine-grained image classification

Xiao, Tianjun; Xu, Yichong; Yang, Kuiyuan; Zhang, Jiaxing; Peng, Yuxin; Zhang, Zheng

doi:10.1109/cvpr.2015.7298685

Cited by 284 publications

(62 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AlexNet [68] and VGG-16 [73]. The experimental results and conclusions are basically consistent with other studies on hierarchical models [8], [16], [55], [72], [74]. Parallelization and grading of neural networks is one of the developmental trends for deep learning.…”

Section: Discussionsupporting

confidence: 86%

“…Recently, a number of studies have been conducted on finegrained classification methods, and most of them provide promising performance in certain fields. Inspired by the design conceptions of parallel networks (e.g., Part-based CNN [8], Two-level Attention CNN [16], MCNN [55], GoogLeNet [72], ResNet [74], and Hypercolumn CNN [90]), we proposed a novel hybrid CNN structure codenamed M-bCNN, which leverages convolutional kernel matrixes to effectively increase the data streams, neurons, and link channels. The matrix-based architecture played an important role and the expected accuracy gains from it were delivered in the fine-grained image classification of wheat leaf diseases.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A Unified Matrix-Based Convolutional Neural Network for Fine-Grained Image Classification of Wheat Leaf Diseases

et al. 2019

View full text Add to dashboard Cite

Fine-grained image classification methods often suffer from the challenge that the subordinate categories within an entry-level category can only be distinguished by subtle differences. Crop disease classification is affected by various visual interferences, including uneven illumination, dew, and equipment jitter. It demands an effective algorithm to accurately discriminate one category from the others. Thus, the representational ability of algorithm needs to be strengthened to learn a robust domain-specific discrimination through an effective way. To address this challenge, a unified convolutional neural network (CNN) denoting the matrix-based convolutional neural network (M-bCNN) was proposed. Its hallmark is the convolutional kernel matrix, whose convolutional layers are arranged parallelly in the form of a matrix, and integrated with DropConnect, exponential linear unit, local response normalization, and so on to defeat over-fitting and vanishing gradient. With a tolerable addition of parameters, it can effectively increase the data streams, neurons, and link channels of the model compared with the commonly used plain networks. Therefore, it will create more non-linear mappings and will enhance the representational ability with a tolerable growth of parameters. The images of winter wheat leaf diseases were utilized as experimental samples for their strong similarities among sub-categories. A total of 16 652 images containing eight categories were collected from Shandong Province, China, and were augmented into 83 260 images. The M-bCNN delivered significant improvements and achieved an average validation accuracy of 96.5% and a testing accuracy of 90.1%; this outperformed AlexNet and VGG-16. The M-bCNN demonstrated accuracy gains with a convolutional kernel matrix in fine-grained image classification. INDEX TERMS Convolutional neural network, fine-grained image classification, deep learning, convolutional kernel matrix, wheat leaf diseases.

show abstract

Section: Discussionsupporting

confidence: 86%

Section: Discussionmentioning

confidence: 99%

A Unified Matrix-Based Convolutional Neural Network for Fine-Grained Image Classification of Wheat Leaf Diseases

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In order to apply fine-grained classification methods to practical applications, many researchers turn to studying how to accurately locate discriminative regions under weakly supervised conditions, and then use CNN to extract features from these regions. Xiao et al designed the first two-level attention model [16] of a weakly supervised classification algorithm, where object-level attention was adopted to select a relevant bounding box of a certain object, while part-level attention was used to locate discriminative components of the object, which achieved 69.7% accuracy on the CUB-200-2011 dataset [17]. Mei et al proposed the recurrent attention convolutional neural network (RA-CNN) [18], which recursively learns discriminative-region attention and feature representation of this region on multiple scales in a mutually reinforcing way, but this method adds computational overhead.…”

Section: Related Workmentioning

confidence: 99%

Bilinear CNN Model for Fine-Grained Classification Based on Subcategory-Similarity Measurement

et al. 2019

View full text Add to dashboard Cite

One of the challenges in fine-grained classification is that subcategories with significant similarity are hard to be distinguished due to the equal treatment of all subcategories in existing algorithms. In order to solve this problem, a fine-grained image classification method by combining a bilinear convolutional neural network (B-CNN) and the measurement of subcategory similarities is proposed. Firstly, an improved weakly supervised localization method is designed to obtain the bounding box of the main object, which allows the model to eliminate the influence of background noise and obtain more accurate features. Then, sample features in the training set are computed by B-CNN so that the fuzzing similarity matrix for measuring interclass similarities can be obtained. To further improve classification accuracy, the loss function is designed by weighting triplet loss and softmax loss. Extensive experiments implemented on two benchmarks datasets, Stanford Cars-196 and Caltech-UCSD Birds-200-2011 (CUB-200-2011), show that the newly proposed method outperforms in accuracy several state-of-the-art weakly supervised classification models.

show abstract

“…The attention model is able to process candidate regions for classification with different resolution and reduce processing cost by focusing on a restricted set of regions. With the help of the attention models, discriminatory power could be focused on the specific parts of the input data, which helps to classify input data [23].…”

Section: Introductionmentioning

confidence: 99%

ECG-Based Heartbeat Classification Using Two-Level Convolutional Neural Network and RR Interval Difference

Xiang

Luo

Zhu

et al. 2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Arrhythmia classification based on electrocardiogram (ECG) is crucial in automatic cardiovascular disease diagnosis. The classification methods used in the current practice largely depend on hand-crafted manual features. However, extracting hand-crafted manual features may introduce significant computational complexity, especially in the transform domains. In this study, an accurate method for patient-specific ECG beat classification is proposed, which adopts morphological features and timing information. As to the morphological features of heartbeat, an attentionbased two-level 1-D CNN is incorporated in the proposed method to extract different grained features automatically by focusing on various parts of a heartbeat. As to the timing information, the difference between previous and post RR intervels is computed as a dynamic feature. Both the extracted morphological features and the interval difference are used by multi-layer perceptron (MLP) for classifing ECG signals. In addition, to reduce memory storage of ECG data and denoise to some extent, an adaptive heartbeat normalization technique is adopted which includes amplitude unification, resolution modification, and signal difference. Based on the MIT-BIH arrhythmia database, the proposed classification method achieved sensitivity Sen = 93.4% and positive predictivity Ppr = 94.9% in ventricular ectopic beat (VEB) detection, sensitivity Sen = 86.3% and positive predictivity Ppr = 80.0% in supraventricular ectopic beat (SVEB) detection, and overall accuracy OA = 97.8% under 6-bit ECG signal resolution. Compared with the state-of-the-art automatic ECG classification methods, these results show that the proposed method acquires comparable accuracy of heartbeat classification though ECG signals are represented by lower resolution. key words: electrocardiogram (ECG), beat classification, convolutional neural network (CNN), biomedical signal processing, multi-layer perceptron (MLP)

show abstract

The application of two-level attention models in deep convolutional neural network for fine-grained image classification

Cited by 284 publications

References 11 publications

A Unified Matrix-Based Convolutional Neural Network for Fine-Grained Image Classification of Wheat Leaf Diseases

A Unified Matrix-Based Convolutional Neural Network for Fine-Grained Image Classification of Wheat Leaf Diseases

Bilinear CNN Model for Fine-Grained Classification Based on Subcategory-Similarity Measurement

ECG-Based Heartbeat Classification Using Two-Level Convolutional Neural Network and RR Interval Difference

Contact Info

Product

Resources

About