arXiv subjects

Tariq M. Khan

Publications and source records attributed to Tariq M. Khan.

23 records · Page 2Linked to original sources

arXiv2022

Neural Network Compression by Joint Sparsity Promotion and Redundancy Reduction

Compression of convolutional neural network models has recently been dominated by pruning approaches. A class of previous works focuses solely on pruning the unimportant filters to achieve network compression. Another important direction is the design of sparsity-inducing constraints which has also been explored in isolation. This paper presents a novel training scheme based on composite constraints that prune redundant filters and minimize their effect on overall network learning via sparsity promotion. Also, as opposed to prior works that employ pseudo-norm-based sparsity-inducing constraints, we propose a sparse scheme based on gradient counting in our framework. Our tests on several pixel-wise segmentation benchmarks show that the number of neurons and the memory footprint of networks in the test phase are significantly reduced without affecting performance. MobileNetV3 and UNet, two well-known architectures, are used to test the proposed scheme. Our network compression method not only results in reduced parameters but also achieves improved performance compared to MobileNetv3, which is an already optimized architecture.

cs.CV↗

arXiv2022

A fast and accurate iris segmentation method using an LoG filter and its zero-crossings

This paper presents a hybrid approach to achieve iris localization based on a Laplacian of Gaussian (LoG) filter, region growing, and zero-crossings of the LoG filter. In the proposed method, an LoG filter with region growing is used to detect the pupil region. Subsequently, zero-crossings of the LoG filter are used to accurately mark the inner and outer circular boundaries. The use of LoG based blob detection along with zero-crossings makes the inner and outer circle detection fast and robust. The proposed method has been tested on three public databases: MMU version 1.0, CASIA-IrisV1 and CASIA-IrisV3- Lamp. The experimental results demonstrate the segmentation accuracy of the proposed method. The robustness of the proposed method is also validated in the presence of noise, such as eyelashes, a reflection of the pupil, Poisson, Gaussian, speckle and salt-and-pepper noise. The comparison with well-known methods demonstrates the superior performance of the proposed method's accuracy and speed.

cs.CV↗

arXiv2022

A Residual Encoder-Decoder Network for Segmentation of Retinal Image-Based Exudates in Diabetic Retinopathy Screening

Diabetic retinopathy refers to the pathology of the retina induced by diabetes and is one of the leading causes of preventable blindness in the world. Early detection of diabetic retinopathy is critical to avoid vision problem through continuous screening and treatment. In traditional clinical practice, the involved lesions are manually detected using photographs of the fundus. However, this task is cumbersome and time-consuming and requires intense effort due to the small size of lesion and low contrast of the images. Thus, computer-assisted diagnosis of diabetic retinopathy based on the detection of red lesions is actively being explored recently. In this paper, we present a convolutional neural network with residual skip connection for the segmentation of exudates in retinal images. To improve the performance of network architecture, a suitable image augmentation technique is used. The proposed network can robustly segment exudates with high accuracy, which makes it suitable for diabetic retinopathy screening. Comparative performance analysis of three benchmark databases: HEI-MED, E-ophtha, and DiaretDB1 is presented. It is shown that the proposed method achieves accuracy (0.98, 0.99, 0.98) and sensitivity (0.97, 0.92, and 0.95) on E-ophtha, HEI-MED, and DiaReTDB1, respectively.

eess.IV↗

arXiv2021

Leveraging Image Complexity in Macro-Level Neural Network Design for Medical Image Segmentation

Recent progress in encoder-decoder neural network architecture design has led to significant performance improvements in a wide range of medical image segmentation tasks. However, state-of-the-art networks for a given task may be too computationally demanding to run on affordable hardware, and thus users often resort to practical workarounds by modifying various macro-level design aspects. Two common examples are downsampling of the input images and reducing the network depth to meet computer memory constraints. In this paper we investigate the effects of these changes on segmentation performance and show that image complexity can be used as a guideline in choosing what is best for a given dataset. We consider four statistical measures to quantify image complexity and evaluate their suitability on ten different public datasets. For the purpose of our experiments we also propose two new encoder-decoder architectures representing shallow and deep networks that are more memory efficient than currently popular networks. Our results suggest that median frequency is the best complexity measure in deciding about an acceptable input downsampling factor and network depth. For high-complexity datasets, a shallow network running on the original images may yield better segmentation results than a deep network running on downsampled images, whereas the opposite may be the case for low-complexity images.

eess.IV↗

arXiv2020

A Derivative-free Method for Quantum Perceptron Training in Multi-layered Neural Networks

In this paper, we present a gradient-free approach for training multi-layered neural networks based upon quantum perceptrons. Here, we depart from the classical perceptron and the elemental operations on quantum bits, i.e. qubits, so as to formulate the problem in terms of quantum perceptrons. We then make use of measurable operators to define the states of the network in a manner consistent with a Markov process. This yields a Dirac-Von Neumann formulation consistent with quantum mechanics. Moreover, the formulation presented here has the advantage of having a computational efficiency devoid of the number of layers in the network. This, paired with the natural efficiency of quantum computing, can imply a significant improvement in efficiency, particularly for deep networks. Finally, but not least, the developments here are quite general in nature since the approach presented here can also be used for quantum-inspired neural networks implemented on conventional computers.

quant-ph↗