MSEC: Multi-Scale Erasure and Confusion for fine-grained image classification

Zhang, Yan; Sun, Yongsheng; Wang, Nian; Gao, Zijian; Chen, Feng; Wang, Chenfei; Tang, Jun

doi:10.1016/j.neucom.2021.03.114

Cited by 10 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tables 7-9 describe the fine-grained image classification results for the CUB, AIR, and CAR datasets, respectively. The "Backbone" column in- ResNet-50 84.7 DFL-CNN [42] 2018 ResNet-50 87.4 iSQRT-COV [11] 2018 ResNet-50 88.1 MAMC [10] 2018 ResNet-101 86.5 HBPASM [43] 2019 ResNet-34 86.8 DBTNet-50 [44] 2019 ResNet-50 87.5 Cross-X [45] 2019 ResNet-50 87.7 DCL [17] 2019 ResNet-50 87.8 TASN [20] 2019 ResNet-50 87.9 S3N [21] 2019 ResNet-50 88.5 MGE-CNN [16] 2019 ResNet-101 89.4 MS-SRP-D [46] 2020 ResNet-50 85.5 BBPL [47] 2021 ResNet 87.62 MFF [48] 2021 ResNet-34 87.1 SMA-Net [49] 2021 ResNet-50 87.71 MSEC [50] 2021 ResNet-50 88.3 SSSNet [22] 2021 ResNet-50 89.0 GHNS [51] 2021 ResNet-50 89.06 CMSEA(Ours) -EfficientNetV2-S 90.63…”

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

CMSEA: Compound Model Scaling With Efficient Attention for Fine-Grained Image Classification

Guang

Liang

2022

IEEE Access

View full text Add to dashboard Cite

The purpose of fine-grained image classification is to distinguish subcategories belonging to the same basic-level category, for example, two hundred subcategories belonging to birds. It has been a challenging topic in the field of computer vision in recent years due to the small inter-class variance among different subcategories (e.g., color and texture) and the large intra-class variance in the same subcategory (e.g., pose and viewpoint). In this paper, we propose a Compound Model Scaling with Efficient Attention (CMSEA) for fine-grained image classification, which carefully balances the various dimensions of width, depth, and image resolution in model scaling. Furthermore, the proposed method utilizes an additional computational low attention module to efficiently learn subtler features from discriminative regions. In addition, regularization and data augmentation were employed to improve accuracy in the training. Extensive experiments demonstrate that CMSEA achieves 90.63%, 94.51%, and 95.19% accuracy on CUB-200-2011, FGVC-Aircraft, and Stanford Cars datasets, respectively. In particular, CMSEA on CUB-200-2011 obtains 2.3% higher accuracy with 18% fewer network parameters than the original approach. Consequently, our method has better accuracy and parameter efficiency compared to most existing methods.

show abstract

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

CMSEA: Compound Model Scaling With Efficient Attention for Fine-Grained Image Classification

Guang

Liang

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The deep learning algorithm is constantly updated and improved, especially the deep convolution neural network algorithm [4][5][6][7][8]29], which has brought huge development space for fine-grained image classification. The research of fine-grained image classification methods can be divided into two directions.…”

Section: Related Workmentioning

confidence: 99%

A study on fine-grained image classification algorithm based on ECA-NET and multi-granularity

2023

IJFET

View full text Add to dashboard Cite

The feature of large intra-class variance in fine-grained image classification is a challenge to the classification task. How to effectively learn the discriminant objects in the graph and find out the small discriminant regions is the key to classification. This paper proposes a weak-supervised fine-grained image classification algorithm based on multi-granularity feature fusion. The ECA module is fused with the classic network ResNet-50 to optimize the residual block to obtain a new basic network to enhance channel attention. Secondly, the local chaos module is introduced into the network to form a new image through random chaos regrouping so that the network can learn local regions with different scales of discrimination and obtain fine-grained feature expressions. The cooperative training of dual network branches makes the overall information and local information complement each other and have better expression. Experimental results on three widely used fine-grained image classification datasets verify that the proposed algorithm improves the accuracy of classification tasks and can effectively identify semantic sensitive features in images.

show abstract

“…For finegrained image classification, it has been a challenge to quickly and efficiently focus on the subtle discriminative details that make subclasses different from each other. Zhang et al (2021) proposed a new multi-scale erasure and confusion method (MSEC) to address the challenge of fine-grained image classification.…”

Section: Deep Learningmentioning

confidence: 99%

3D FRN-ResNet: An Automated Major Depressive Disorder Structural Magnetic Resonance Imaging Data Identification Framework

Hong

Huang

et al. 2022

Front. Aging Neurosci.

View full text Add to dashboard Cite

Major Depressive Disorder (MDD) is the most prevalent psychiatric disorder, seriously affecting people’s quality of life. Manually identifying MDD from structural magnetic resonance imaging (sMRI) images is laborious and time-consuming due to the lack of clear physiological indicators. With the development of deep learning, many automated identification methods have been developed, but most of them stay in 2D images, resulting in poor performance. In addition, the heterogeneity of MDD also results in slightly different changes reflected in patients’ brain imaging, which constitutes a barrier to the study of MDD identification based on brain sMRI images. We propose an automated MDD identification framework in sMRI data (3D FRN-ResNet) to comprehensively address these challenges, which uses 3D-ResNet to extract features and reconstruct them based on feature maps. Notably, the 3D FRN-ResNet fully exploits the interlayer structure information in 3D sMRI data and preserves most of the spatial details as well as the location information when converting the extracted features into vectors. Furthermore, our model solves the feature map reconstruction problem in closed form to produce a straightforward and efficient classifier and dramatically improves model performance. We evaluate our framework on a private brain sMRI dataset of MDD patients. Experimental results show that the proposed model exhibits promising performance and outperforms the typical other methods, achieving the accuracy, recall, precision, and F1 values of 0.86776, 0.84237, 0.85333, and 0.84781, respectively.

show abstract

MSEC: Multi-Scale Erasure and Confusion for fine-grained image classification

Cited by 10 publications

References 13 publications

CMSEA: Compound Model Scaling With Efficient Attention for Fine-Grained Image Classification

CMSEA: Compound Model Scaling With Efficient Attention for Fine-Grained Image Classification

A study on fine-grained image classification algorithm based on ECA-NET and multi-granularity

3D FRN-ResNet: An Automated Major Depressive Disorder Structural Magnetic Resonance Imaging Data Identification Framework

Contact Info

Product

Resources

About