Deep Model Compression based on the Training History

Basha, S. H. Shabbeer; Farazuddin, Mohammad; Pulabaigari, Viswanath; Dubey, Shiv Ram; Mukherjee, Snehasis

doi:10.48550/arxiv.2102.00160

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…VGG16 is a kind of Visual Geometry Group convolutional neural network, and this model was presented by K. Simonyan and A. Zisserman from the University of Oxford in the paper "Very Deep Convolutional Networks for Large-Scale Image Recognition." The VGG-16 network accomplishes 92.7% top-5 train and test accuracy in ImageNet, a dataset of over 14 million images of 1000 classes [34]. In VGG-16, more kernels are changed with the different numbers of 3 × 3 filters to extract complex features cheaply.…”

Section: Vgg-16mentioning

confidence: 99%

Improving Respiratory Infection Diagnosis with Deep Learning and Combinatorial Fusion: A Two-Stage Approach Using Chest X-ray Imaging

Pan,

Kumar,

Wen

et al. 2024

Diagnostics

View full text Add to dashboard Cite

The challenges of respiratory infections persist as a global health crisis, placing substantial stress on healthcare infrastructures and necessitating ongoing investigation into efficacious treatment modalities. The persistent challenge of respiratory infections, including COVID-19, underscores the critical need for enhanced diagnostic methodologies to support early treatment interventions. This study introduces an innovative two-stage data analytics framework that leverages deep learning algorithms through a strategic combinatorial fusion technique, aimed at refining the accuracy of early-stage diagnosis of such infections. Utilizing a comprehensive dataset compiled from publicly available lung X-ray images, the research employs advanced pre-trained deep learning models to navigate the complexities of disease classification, addressing inherent data imbalances through methodical validation processes. The core contribution of this work lies in its novel application of combinatorial fusion, integrating select models to significantly elevate diagnostic precision. This approach not only showcases the adaptability and strength of deep learning in navigating the intricacies of medical imaging but also marks a significant step forward in the utilization of artificial intelligence to improve outcomes in healthcare diagnostics. The study’s findings illuminate the path toward leveraging technological advancements in enhancing diagnostic accuracies, ultimately contributing to the timely and effective treatment of respiratory diseases.

show abstract

Section: Vgg-16mentioning

confidence: 99%

Improving Respiratory Infection Diagnosis with Deep Learning and Combinatorial Fusion: A Two-Stage Approach Using Chest X-ray Imaging

Pan,

Kumar,

Wen

et al. 2024

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Figure 3(b) depicts the FLOPS performed by the neural networks, as measured using the profiler from e-Lab 2 .FLOPS per convolution is given by 𝐹𝐿𝑂𝑃 𝑐𝑜𝑛𝑣 = 𝐹 • 𝐹 • 𝐶 𝑖𝑛 • 𝐻 𝑜𝑢𝑡 • 𝑊 𝑜𝑢𝑡 • 𝐶 𝑜𝑢𝑡 , where 𝐹 • 𝐹 is the spatial dimension of the filter, 𝐶 𝑖𝑛 and 𝐶 𝑜𝑢𝑡 are the number of input and output channels, respectively, and 𝐻 𝑜𝑢𝑡 • 𝑊 𝑜𝑢𝑡 is the output shape[45]. As the number of patches (𝑁 𝑝 ) increases, the size of each patch decreases quadratically, (ℎ𝑖 𝑠𝑖𝑧𝑒 𝑁 𝑝 ⁄ )2 .…”

mentioning

confidence: 99%

Two-stage semantic segmentation in neural networks

Silva

Cruz

Gonçalves

et al. 2023

Fifteenth International Conference on Machine Vision (ICMV 2022)

View full text Add to dashboard Cite

Semantic segmentation consists of classifying each pixel according to a set of classes. This process is particularly slow for high-resolution images, which are present in many applications, ranging from biomedicine to the automotive industry. In this work, we propose an algorithm targeted to segment high-resolution images based on two stages. During stage 1, a lower-resolution interpolation of the image is the input of a first neural network, whose low-resolution output is resized to the original resolution. Then, in stage 2, the probabilities resulting from stage 1 are divided into contiguous patches, with less confident ones being collected and refined by a second neural network. The main novelty of this algorithm is the aggregation of the low-resolution result from stage 1 with the high-resolution patches from stage 2. We propose the U-Net architecture segmentation, evaluated in six databases. Our method shows similar results to the baseline regarding the Dice coefficient, with fewer arithmetic operations.

show abstract

Deep Model Compression based on the Training History

Cited by 2 publications

References 0 publications

Improving Respiratory Infection Diagnosis with Deep Learning and Combinatorial Fusion: A Two-Stage Approach Using Chest X-ray Imaging

Improving Respiratory Infection Diagnosis with Deep Learning and Combinatorial Fusion: A Two-Stage Approach Using Chest X-ray Imaging

Two-stage semantic segmentation in neural networks

Contact Info

Product

Resources

About