BNET: Batch Normalization With Enhanced Linear Transformation

Xu, Yuhui; Xie, Lingxi; Xie, Cihang; Dai, Wenrui; Mei, Jieru; Qiao, Siyuan; Shen, Wei; Xiong, Hongkai; Yuille, Alan

doi:10.1109/tpami.2023.3235369

Cited by 7 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Batch normalization (BN) is one such method that normalizes activations from the preceding layer across the current mini-batch [20]. This involves computing independent means and variances for each feature, followed by a linear transformation to normalize values [21]. Layer normalization (LN), on the other hand, normalizes layer activations across feature dimensions, independently calculating means and variances for each sample within the mini-batch.…”

Section: Normalizationsmentioning

confidence: 99%

Enhancing the UNet3+ architecture for deep learning segmentation of kidneys and cysts in autosomal dominant polycystic kidney disease (ADPKD)

Krishnan,

Schmidt,

Onuoha

et al. 2024

Medical Imaging 2024: Clinical and Biomedical Imaging

View full text Add to dashboard Cite

Autosomal Dominant Polycystic Kidney Disease (ADPKD) presents a significant clinical challenge, demanding precise and efficient diagnostic tools. In this context, this research addresses the imperative need for accurate diagnosis of ADPKD through the refinement of deep learning models, specifically UNet++ and UNet3+, for precise segmentation of renal structures and cysts in T2W MRI images. By incorporating residual staging, switch normalization, and concatenated skip connections (CSC), our proposed models, rUNet++ and rUNet3+, aim to enhance feature fusion, extraction, and segmentation accuracy. Utilizing a dataset of 760 MRI images from 95 patients, we trained, validated, and tested the models, assigning images exclusively to each set to eliminate bias. The ground truth was established through a semi-automated technique. Evaluation metrics, including Dice Similarity Coefficient (DSC) and Mean Surface Distance (MSD), demonstrated improved performance for rUNet++ and rUNet3+, with the latter exhibiting the highest test minimum DSCs for kidneys and the former for the cysts. The proposed models achieved average DSC scores of 0.95±0.02 and 0.94±0.03 respectively for kidneys and 0.88±0.04 and 0.86±0.05 for cysts. The clinical significance of these findings lies in the enhanced precision of total kidney volume quantification, a vital biomarker for ADPKD diagnosis. This automated approach not only streamlines the diagnostic process but also reduces manual involvement, addressing a crucial aspect in the clinical workflow. By presenting a modified deep learning architecture, this research contributes to advancing the technological landscape in medical imaging, offering a promising avenue for improving the clinical management of ADPKD through accurate and efficient segmentation.

show abstract

Section: Normalizationsmentioning

confidence: 99%

Enhancing the UNet3+ architecture for deep learning segmentation of kidneys and cysts in autosomal dominant polycystic kidney disease (ADPKD)

Krishnan,

Schmidt,

Onuoha

et al. 2024

Medical Imaging 2024: Clinical and Biomedical Imaging

View full text Add to dashboard Cite

show abstract

“…In order to further enrich the fitting ability of the backbone network, sequence-based functions learn global information by changing the input of adjacent regions, similar to BNET [21], where H, W, and C are their width, height, and number of channels, respectively. The activation function is represented as (3)…”

Section: Deep Training Strategy and Nonlinear Activationmentioning

confidence: 99%

Taoism-Net: A Fruit Tree Segmentation Model Based on Minimalism Design for UAV Camera

Mai,

Zheng,

Luo

et al. 2024

Agronomy

View full text Add to dashboard Cite

The development of precision agriculture requires unmanned aerial vehicles (UAVs) to collect diverse data, such as RGB images, 3D point clouds, and hyperspectral images. Recently, convolutional networks have made remarkable progress in downstream visual tasks, while often disregarding the trade-off between accuracy and speed in UAV-based segmentation tasks. The study aims to provide further valuable insights using an efficient model named Taoism-Net. The findings include the following: (1) Prescription maps in agricultural UAVs requires pixel-level precise segmentation, with many focusing solely on accuracy at the expense of real-time processing capabilities, being incapable of satisfying the expectations of practical tasks. (2) Taoism-Net is a refreshingly segmented model, overcoming the challenges of complexity in deep learning, based on minimalist design, which is used to generate prescription maps through pixel level classification mapping of geodetic coordinates (the lychee tree aerial dataset in Guangdong is used for experiments). (3) Compared with mainstream lightweight models or mature segmentation algorithms, Taoism-Net achieves significant improvements, including an improvement of at least 4.8% in mIoU, and manifested a superior performance in the accuracy–latency curve. (4) “The greatest truths are concise” is a saying widely spread by ancient Taoism, indicating that the most fundamental approach is reflected through the utmost minimalism; moreover, Taoism-Net expects to a build bridge between academic research and industrial deployment, for example, UAVs in precision agriculture.

show abstract

“…Moreover, batch normalization (BN) is incorporated to enhance the stability and accelerate the convergence speed throughout the neural network's up-sampling procedure. The utilization of BN enables data standardization, facilitates smaller regularization, diminishes generalization errors, and enhances overall network performance [50].…”

Section: Raindrop Removal Networkmentioning

confidence: 99%

MARR-GAN: Memristive Attention Recurrent Residual Generative Adversarial Network for Raindrop Removal

Chai,

Liu

2024

Micromachines

View full text Add to dashboard Cite

Since machine learning techniques for raindrop removal have not been capable of completely removing raindrops and have failed to take into account the constraints of edge devices with limited resources, a novel software-hardware co-designed method with a memristor for raindrop removal, named memristive attention recurrent residual generative adversarial network (MARR-GAN), is introduced in this research. A novel raindrop-removal network is specifically designed based on attention gate connections and recurrent residual convolutional blocks. By replacing the basic convolution unit with recurrent residual convolution unit, improved capturing of the changes in raindrop appearance over time is achieved, while preserving the position and shape information in the image. Additionally, an attention gate is utilized instead of the original skip connection to enhance the overall structural understanding and local detail preservation, facilitating a more comprehensive removal of raindrops across various areas of the image. Furthermore, a hardware implementation scheme for MARR-GAN is presented in this paper, where deep learning algorithms are seamlessly integrated with neuro inspired computing chips, utilizing memristor crossbar arrays for accelerated real-time image-data processing. Compelling evidence of the efficacy and superiority of MARR-GAN in raindrop removal and image restoration is provided by the results of the empirical study.

show abstract

BNET: Batch Normalization With Enhanced Linear Transformation

Cited by 7 publications

References 31 publications

Enhancing the UNet3+ architecture for deep learning segmentation of kidneys and cysts in autosomal dominant polycystic kidney disease (ADPKD)

Enhancing the UNet3+ architecture for deep learning segmentation of kidneys and cysts in autosomal dominant polycystic kidney disease (ADPKD)

Taoism-Net: A Fruit Tree Segmentation Model Based on Minimalism Design for UAV Camera

MARR-GAN: Memristive Attention Recurrent Residual Generative Adversarial Network for Raindrop Removal

Contact Info

Product

Resources

About