arXiv subjects

Dilip K. Prasad

Publications and source records attributed to Dilip K. Prasad.

33 records · Page 2Linked to original sources

arXiv2023

Patch Gradient Descent: Training Neural Networks on Very Large Images

Traditional CNN models are trained and tested on relatively low resolution images (<300 px), and cannot be directly operated on large-scale images due to compute and memory constraints. We propose Patch Gradient Descent (PatchGD), an effective learning strategy that allows to train the existing CNN architectures on large-scale images in an end-to-end manner. PatchGD is based on the hypothesis that instead of performing gradient-based updates on an entire image at once, it should be possible to achieve a good solution by performing model updates on only small parts of the image at a time, ensuring that the majority of it is covered over the course of iterations. PatchGD thus extensively enjoys better memory and compute efficiency when training models on large scale images. PatchGD is thoroughly evaluated on two datasets - PANDA and UltraMNIST with ResNet50 and MobileNetV2 models under different memory constraints. Our evaluation clearly shows that PatchGD is much more stable and efficient than the standard gradient-descent method in handling large images, and especially when the compute memory is limited.

cs.CV↗

arXiv2022

UltraMNIST Classification: A Benchmark to Train CNNs for Very Large Images

Convolutional neural network (CNN) approaches available in the current literature are designed to work primarily with low-resolution images. When applied on very large images, challenges related to GPU memory, smaller receptive field than needed for semantic correspondence and the need to incorporate multi-scale features arise. The resolution of input images can be reduced, however, with significant loss of critical information. Based on the outlined issues, we introduce a novel research problem of training CNN models for very large images, and present 'UltraMNIST dataset', a simple yet representative benchmark dataset for this task. UltraMNIST has been designed using the popular MNIST digits with additional levels of complexity added to replicate well the challenges of real-world problems. We present two variants of the problem: 'UltraMNIST classification' and 'Budget-aware UltraMNIST classification'. The standard UltraMNIST classification benchmark is intended to facilitate the development of novel CNN training methods that make the effective use of the best available GPU resources. The budget-aware variant is intended to promote development of methods that work under constrained GPU memory. For the development of competitive solutions, we present several baseline models for the standard benchmark and its budget-aware variant. We study the effect of reducing resolution on the performance and present results for baseline models involving pretrained backbones from among the popular state-of-the-art models. Finally, with the presented benchmark dataset and the baselines, we hope to pave the ground for a new generation of CNN methods suitable for handling large images in an efficient and resource-light manner.

cs.CV↗

arXiv2021

Physics-guided Loss Functions Improve Deep Learning Performance in Inverse Scattering

Solving electromagnetic inverse scattering problems (ISPs) is challenging due to the intrinsic nonlinearity, ill-posedness, and expensive computational cost. Recently, deep neural network (DNN) techniques have been successfully applied on ISPs and shown potential of superior imaging over conventional methods. In this paper, we analyse the analogy between DNN solvers and traditional iterative algorithms and discuss how important physical phenomena cannot be effectively incorporated in the training process. We show the importance of including near-field priors in the learning process of DNNs. To this end, we propose new designs of loss functions which incorporate multiple-scattering based near-field quantities (such as scattered fields or induced currents within domain of interest). Effects of physics-guided loss functions are studied using a variety of numerical experiments. Pros and cons of the investigated ISP solvers with different loss functions are summarized.

cs.LG↗

arXiv2020

Neural network based country wise risk prediction of COVID-19

The recent worldwide outbreak of the novel coronavirus (COVID-19) has opened up new challenges to the research community. Artificial intelligence (AI) driven methods can be useful to predict the parameters, risks, and effects of such an epidemic. Such predictions can be helpful to control and prevent the spread of such diseases. The main challenges of applying AI is the small volume of data and the uncertain nature. Here, we propose a shallow long short-term memory (LSTM) based neural network to predict the risk category of a country. We have used a Bayesian optimization framework to optimize and automatically design country-specific networks. The results show that the proposed pipeline outperforms state-of-the-art methods for data of 180 countries and can be a useful tool for such risk categorization. We have also experimented with the trend data and weather data combined for the prediction. The outcome shows that the weather does not have a significant role. The tool can be used to predict long-duration outbreak of such an epidemic such that we can take preventive steps earlier

q-bio.PE↗

arXiv2020

Auxiliary Network: Scalable and agile online learning for dynamic system with inconsistently available inputs

Streaming classification methods assume the number of input features is fixed and always received. But in many real-world scenarios demand is some input features are reliable while others are unreliable or inconsistent. In this paper, we propose a novel deep learning-based model called Auxiliary Network (Aux-Net), which is scalable and agile. It employs a weighted ensemble of classifiers to give a final outcome. The Aux-Net model is based on the hedging algorithm and online gradient descent. It employs a model of varying depth in an online setting using single pass learning. Aux-Net is a foundational work towards scalable neural network model for a dynamic complex environment requiring ad hoc or inconsistent input data. The efficacy of Aux-Net is shown on public dataset.

cs.LG↗

arXiv2020

Simulation-supervised deep learning for analysing organelles states and behaviour in living cells

In many real-world scientific problems, generating ground truth (GT) for supervised learning is almost impossible. The causes include limitations imposed by scientific instrument, physical phenomenon itself, or the complexity of modeling. Performing artificial intelligence (AI) tasks such as segmentation, tracking, and analytics of small sub-cellular structures such as mitochondria in microscopy videos of living cells is a prime example. The 3D blurring function of microscope, digital resolution from pixel size, optical resolution due to the character of light, noise characteristics, and complex 3D deformable shapes of mitochondria, all contribute to making this problem GT hard. Manual segmentation of 100s of mitochondria across 1000s of frames and then across many such videos is not only herculean but also physically inaccurate because of the instrument and phenomena imposed limitations. Unsupervised learning produces less than optimal results and accuracy is important if inferences relevant to therapy are to be derived. In order to solve this unsurmountable problem, we bring modeling and deep learning to a nexus. We show that accurate physics based modeling of microscopy data including all its limitations can be the solution for generating simulated training datasets for supervised learning. We show here that our simulation-supervised segmentation approach is a great enabler for studying mitochondrial states and behaviour in heart muscle cells, where mitochondria have a significant role to play in the health of the cells. We report unprecedented mean IoU score of 91% for binary segmentation (19% better than the best performing unsupervised approach) of mitochondria in actual microscopy videos of living cells. We further demonstrate the possibility of performing multi-class classification, tracking, and morphology associated analytics at the scale of individual mitochondrion.

eess.IV↗

arXiv2020

Single image dehazing for a variety of haze scenarios using back projected pyramid network

Learning to dehaze single hazy images, especially using a small training dataset is quite challenging. We propose a novel generative adversarial network architecture for this problem, namely back projected pyramid network (BPPNet), that gives good performance for a variety of challenging haze conditions, including dense haze and inhomogeneous haze. Our architecture incorporates learning of multiple levels of complexities while retaining spatial context through iterative blocks of UNets and structural information of multiple scales through a novel pyramidal convolution block. These blocks together for the generator and are amenable to learning through back projection. We have shown that our network can be trained without over-fitting using as few as 20 image pairs of hazy and non-hazy images. We report the state of the art performances on NTIRE 2018 homogeneous haze datasets for indoor and outdoor images, NTIRE 2019 denseHaze dataset, and NTIRE 2020 non-homogeneous haze dataset.

eess.IV↗

arXiv2020

Deep learning architecture LightOCT for diagnostic decision support using optical coherence tomography images of biological samples

Optical coherence tomography (OCT) is being increasingly adopted as a label-free and non-invasive technique for biomedical applications such as cancer and ocular disease diagnosis. Diagnostic information for these tissues is manifest in textural and geometric features of the OCT images, which are used by human expertise to interpret and triage. However, it suffers delays due to the long process of the conventional diagnostic procedure and shortage of human expertise. Here, a custom deep learning architecture, LightOCT, is proposed for the classification of OCT images into diagnostically relevant classes. LightOCT is a convolutional neural network with only two convolutional layers and a fully connected layer, but it is shown to provide excellent training and test results for diverse OCT image datasets. We show that LightOCT provides 98.9% accuracy in classifying 44 normal and 44 malignant (invasive ductal carcinoma) breast tissue volumetric OCT images. Also, >96% accuracy in classifying public datasets of ocular OCT images as normal, age-related macular degeneration and diabetic macular edema. Additionally, we show ~96% test accuracy for classifying retinal images as belonging to choroidal neovascularization, diabetic macular edema, drusen, and normal samples on a large public dataset of more than 100,000 images. The performance of the architecture is compared with transfer learning based deep neural networks. Through this, we show that LightOCT can provide significant diagnostic support for a variety of OCT images with sufficient training and minimal hyper-parameter tuning. The trained LightOCT networks for the three-classification problem will be released online to support transfer learning on other datasets.

physics.med-ph↗

arXiv2019

Are object detection assessment criteria ready for maritime computer vision?

Maritime vessels equipped with visible and infrared cameras can complement other conventional sensors for object detection. However, application of computer vision techniques in maritime domain received attention only recently. The maritime environment offers its own unique requirements and challenges. Assessment of the quality of detections is a fundamental need in computer vision. However, the conventional assessment metrics suitable for usual object detection are deficient in the maritime setting. Thus, a large body of related work in computer vision appears inapplicable to the maritime setting at the first sight. We discuss the problem of defining assessment metrics suitable for maritime computer vision. We consider new bottom edge proximity metrics as assessment metrics for maritime computer vision. These metrics indicate that existing computer vision approaches are indeed promising for maritime computer vision and can play a foundational role in the emerging field of maritime computer vision.

cs.CV↗

arXiv2019

TMAV: Temporal Motionless Analysis of Video using CNN in MPSoC

Analyzing video for traffic categorization is an important pillar of Intelligent Transport Systems. However, it is difficult to analyze and predict traffic based on image frames because the representation of each frame may vary significantly within a short time period. This also would inaccurately represent the traffic over a longer period of time such as the case of video. We propose a novel bio-inspired methodology that integrates analysis of the previous image frames of the video to represent the analysis of the current image frame, the same way a human being analyzes the current situation based on past experience. In our proposed methodology, called IRON-MAN (Integrated Rational prediction and Motionless ANalysis), we utilize Bayesian update on top of the individual image frame analysis in the videos and this has resulted in highly accurate prediction of Temporal Motionless Analysis of the Videos (TMAV) for most of the chosen test cases. The proposed approach could be used for TMAV using Convolutional Neural Network (CNN) for applications where the number of objects in an image is the deciding factor for prediction and results also show that our proposed approach outperforms the state-of-the-art for the chosen test case. We also introduce a new metric named, Energy Consumption per Training Image (ECTI). Since, different CNN based models have different training capability and computing resource utilization, some of the models are more suitable for embedded device implementation than the others, and ECTI metric is useful to assess the suitability of using a CNN model in multi-processor systems-on-chips (MPSoCs) with a focus on energy consumption and reliability in terms of lifespan of the embedded device using these MPSoCs.

cs.CV↗

arXiv2019

Can We Automate Diagrammatic Reasoning?

Learning to solve diagrammatic reasoning (DR) can be a challenging but interesting problem to the computer vision research community. It is believed that next generation pattern recognition applications should be able to simulate human brain to understand and analyze reasoning of images. However, due to the lack of benchmarks of diagrammatic reasoning, the present research primarily focuses on visual reasoning that can be applied to real-world objects. In this paper, we present a diagrammatic reasoning dataset that provides a large variety of DR problems. In addition, we also propose a Knowledge-based Long Short Term Memory (KLSTM) to solve diagrammatic reasoning problems. Our proposed analysis is arguably the first work in this research area. Several state-of-the-art learning frameworks have been used to compare with the proposed KLSTM framework in the present context. Preliminary results indicate that the domain is highly related to computer vision and pattern recognition research with several challenging avenues.

cs.CV↗

arXiv2018

Polygonal approximation of digital planar curve using novel significant measure

This paper presents an iterative smoothing technique for polygonal approximation of digital image boundary. The technique starts with finest initial segmentation points of a curve. The contribution of initially segmented points towards preserving the original shape of the image boundary is determined by computing the significant measure of every initial segmentation points which is sensitive to sharp turns, which may be missed easily when conventional significant measures are used for detecting dominant points. The proposed method differentiates between the situations when a point on the curve between two points on a curve projects directly upon the line segment or beyond this line segment. It not only identifies these situations, but also computes its significant contribution for these situations differently. This situation-specific treatment allows preservation of points with high curvature even as revised set of dominant points are derived. The experimental results show that the proposed technique competes well with the state of the art techniques.

cs.CV↗

arXiv2018

Enabling Grasp Action: Generalized Evaluation of Grasp Stability via Contact Stiffness from Contact Mechanics Insight

Performing a grasp is a pivotal capability for a robotic gripper. We propose a new evaluation approach of grasping stability via constructing a model of grasping stiffness based on the theory of contact mechanics. First, the mathematical models are built to explore soft contact and the general grasp stiffness between a finger and an object. Next, the grasping stiffness matrix is constructed to reflect the normal, tangential and torsion stiffness coefficients. Finally, we design two grasping cases to verify the proposed measurement criterion of grasping stability by comparing different grasping configurations. Specifically, a standard grasping index is used and compared with the minimum eigenvalue index of the constructed grasping stiffness we built. The comparison result reveals a similar tendency between them for measuring the grasping stability and thus, validates the proposed approach.

cs.RO↗

arXiv2013

Geometric primitive feature extraction - concepts, algorithms, and applications

This thesis presents important insights and concepts related to the topic of the extraction of geometric primitives from the edge contours of digital images. Three specific problems related to this topic have been studied, viz., polygonal approximation of digital curves, tangent estimation of digital curves, and ellipse fitting anddetection from digital curves. For the problem of polygonal approximation, two fundamental problems have been addressed. First, the nature of the performance evaluation metrics in relation to the local and global fitting characteristics has been studied. Second, an explicit error bound of the error introduced by digitizing a continuous line segment has been derived and used to propose a generic non-heuristic parameter independent framework which can be used in several dominant point detection methods. For the problem of tangent estimation for digital curves, a simple method of tangent estimation has been proposed. It is shown that the method has a definite upper bound of the error for conic digital curves. It has been shown that the method performs better than almost all (seventy two) existing tangent estimation methods for conic as well as several non-conic digital curves. For the problem of fitting ellipses on digital curves, a geometric distance minimization model has been considered. An unconstrained, linear, non-iterative, and numerically stable ellipse fitting method has been proposed and it has been shown that the proposed method has better selectivity for elliptic digital curves (high true positive and low false positive) as compared to several other ellipse fitting methods. For the problem of detecting ellipses in a set of digital curves, several innovative and fast pre-processing, grouping, and hypotheses evaluation concepts applicable for digital curves have been proposed and combined to form an ellipse detection method.

cs.CV↗

arXiv2013

Object Detection in Real Images

Object detection and recognition are important problems in computer vision. Since these problems are meta-heuristic, despite a lot of research, practically usable, intelligent, real-time, and dynamic object detection/recognition methods are still unavailable. We propose a new object detection/recognition method, which improves over the existing methods in every stage of the object detection/recognition process. In addition to the usual features, we propose to use geometric shapes, like linear cues, ellipses and quadrangles, as additional features. The full potential of geometric cues is exploited by using them to extract other features in a robust, computationally efficient, and less meta-heuristic manner. We also propose a new hierarchical codebook, which provides good generalization and discriminative properties. The codebook enables fast multi-path inference mechanisms based on propagation of conditional likelihoods, that make it robust to occlusion and noise. It has the capability of dynamic learning. We also propose a new learning method that has generative and discriminative learning capabilities, does not need large and fully supervised training dataset, and is capable of online learning. The preliminary work of detecting geometric shapes in real images has been completed. This preliminary work is the focus of this report. Future path for realizing the proposed object detection/recognition method is also discussed in brief.

cs.CV↗