Exponential Information Bottleneck Theory Against Intra-Attribute Variations for Pedestrian Attribute Recognition

Wu, Junyi; Huang, Yan; Gao, Min; Gao, Zhipeng; Zhao, Jianqiang; Shi, Jieming; Zhang, Anguo

doi:10.1109/tifs.2023.3311584

Cited by 4 publications

(2 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been additional studies combining CNNs with assistant approaches, particularly in the context of data augmentation (Zhang et al, 2022 ; Wu et al, 2023b ). The data augmentation methods used in SAR ATR can be broadly categorized into spatial information-related methods (Wagner, 2016 ; Pei et al, 2018a ) and speckle noise-related methods (Xu et al, 2017 ).…”

Section: Introductionmentioning

confidence: 99%

Weighted residual network for SAR automatic target recognition with data augmentation

Li,

Peng

2023

Front. Neurorobot.

View full text Add to dashboard Cite

IntroductionDecades of research have been dedicated to overcoming the obstacles inherent in synthetic aperture radar (SAR) automatic target recognition (ATR). The rise of deep learning technologies has brought a wave of new possibilities, demonstrating significant progress in the field. However, challenges like the susceptibility of SAR images to noise, the requirement for large-scale training datasets, and the often protracted duration of model training still persist.MethodsThis paper introduces a novel data augmentation strategy to address these issues. Our method involves the intentional addition and subsequent removal of speckle noise to artificially enlarge the scope of training data through noise perturbation. Furthermore, we propose a modified network architecture named weighted ResNet, which incorporates residual strain controls for enhanced performance. This network is designed to be computationally efficient and to minimize the amount of training data required.ResultsThrough rigorous experimental analysis, our research confirms that the proposed data augmentation method, when used in conjunction with the weighted ResNet model, significantly reduces the time needed for training. It also improves the SAR ATR capabilities.DiscussionCompared to existing models and methods tested, the combination of our data augmentation scheme and the weighted ResNet framework achieves higher computational efficiency and better recognition accuracy in SAR ATR applications. This suggests that our approach could be a valuable advancement in the field of SAR image analysis.

show abstract

Section: Introductionmentioning

confidence: 99%

Weighted residual network for SAR automatic target recognition with data augmentation

Li,

Peng

2023

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

“…In the context of DNNs, information theory has been instrumental in explaining and optimizing their performance (Zhang and Li, 2019 ; Zhang et al, 2022 , 2023 ). For instance, the information bottleneck theory has shed light on the abstract representations of neural networks, while entropy and mutual information have been used to evaluate model complexity and generalization performance (Wu et al, 2023 ). This Research Topic aims to explore the intersection of information theory and DNNs, two fields that have profoundly impacted the understanding and advancement of neural networks and their applications.…”

mentioning

confidence: 99%

Editorial: Information theory meets deep neural networks: theory and applications

Zhang,

Zhao

2024

Front. Neurosci.

Self Cite

View full text Add to dashboard Cite

Vision Transformer based UNet with Multi-Head Attention for Medical Image Segmentation

Yu,

Gao,

et al. 2024

2024 36th Chinese Control and Decision Conference (CCDC)

View full text Add to dashboard Cite

Exponential Information Bottleneck Theory Against Intra-Attribute Variations for Pedestrian Attribute Recognition

Cited by 4 publications

References 52 publications

Weighted residual network for SAR automatic target recognition with data augmentation

Weighted residual network for SAR automatic target recognition with data augmentation

Editorial: Information theory meets deep neural networks: theory and applications

Vision Transformer based UNet with Multi-Head Attention for Medical Image Segmentation

Contact Info

Product

Resources

About