Department of Computer Science & Engineering

&ldquo;IIT Jodhpur is committed to impart quality education to facilitate the creation of qualified, competent and responsible human resources to meet the emerging technological challenges of the world. It is working towards creating an equitable learning platform that is positive, accessible and effective in the face of the modern societal and scientific advancements.

Flexibility in curriculum, in all its academic programs, encompassing elements of teaching, research, creativity, innovation and entrepreneurship is the most unique feature of IIT Jodhpur. The Department of Science and Technology (DST), under the National Mission on Cyber Physical Systems, has identified IIT Jodhpur as a Technology &amp; Innovation Hub in the area of Augmented Reality and Virtual Reality. The institute has also been nominated as the coordinator for the Jodhpur City and Knowledge Cluster by the Office of Principal Scientific Adviser, Government of India.

The sprawling 852-acre IIT Jodhpur campus is a majestic tribute to the deep-rooted diverse cultural heritage of the region. The campus is an architectural masterpiece, which is slated to become an international exemplar of sustainability with net-zero energy, and advanced water and waste management strategies.&rdquo;

IIT Jodhpur

3D reconstruction of human body model from a monocular image is an under-constrained and challenging yet desired research problem in computer vision. Recently proposed multi-layered shape representation called PeeledHuman attempted a sparse non-parametric 2D representation that can handle severe self-occlusion. However, the key limitation of their PeeledHuman model is that the predicted depth maps of self-occluded parts are sparse and noisy, and hence after back-projection lead to distorted body parts and sometimes with discontinuity between them. In this work, proposed to introduce Peeled Segmentation map representation in a coarse-to-fine refinement framework which consist of a cascade three networks namely, PeelGAN, PSegGAN and RefGAN. At first, we use original PeeledHuman as baseline model to predict initial coarse estimation of peeled depth maps from input RGB image. These peeled maps are subsequently fed as input along with monocular RGB image to our novel PSegGAN which predict Peeled Segmentation maps in a generative fashion. Finally, we feed these peeled segmentation maps as additional context along with monocular input image to our RefGAN which predicts the refined peeled RBG and Depth maps. This also provides an additional output of 3D semantic segmentation of the reconstructed shape. We perform thorough empirical evaluation over four publicly available datasets to demonstrate superiority of our model. © 2021 ACM.

World University root node

ACM International Conference Proceeding Series

Coarse-to-fine 3D clothed human reconstruction using peeled semantic segmentation context

AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing Label Features from Multi-Modal Embeddings

Neurocomputing

Calibrating feature maps for deep CNNs

Few-shot learning is an almost unexplored area in the field of medical image analysis. We propose a method for few-shot diagnosis of diseases and conditions from chest x-rays using discriminative ensemble learning. Our design involves a CNN-based coarse-learner in the first step to learn the general characteristics of chest x-rays. In the second step, we introduce a saliency-based classifier to extract disease-specific salient features from the output of the coarse-learner and classify based on the salient features. We propose a novel discriminative autoencoder ensemble to design the saliency-based classifier. The classification of the diseases is performed based on the salient features. Our algorithm proceeds through meta-training and meta-testing. During the training phase of meta-training, we train the coarse-learner. However, during the training phase of meta-testing, we train only the saliency-based classifier. Thus, our method is first-of-its-kind where the training phase of meta-training and the training phase of meta-testing are architecturally disjoint, making the method modular and easily adaptable to new tasks requiring the training of only the saliency-based classifier. Experiments show as high as ∼19% improvement in terms of F1 score compared to the baseline in the diagnosis of chest x-rays from publicly available datasets. © 2020

Medical Image Analysis

Discriminative ensemble learning for few-shot chest x-ray diagnosis

Structural Causal Modelling (SCM) with its intervention analysis is one of the promising modelling approach that assists in data driven decision making. SCM not only overcomes the black box modelling associated with most of the classification algorithms but also gives enterprises an opportunity to perform intervention analysis without having to perform randomized controlled experiments. But the large volume of enterprises' data pose challenges in learning the causal structure as existing algorithms are not suitable to learn from data present in Distributed File System (DFS). Hence algorithm presented in this paper, proposes a novel variation to PC-Stable algorithm to efficiently learn the causal structure from data present in DFS - thus enabling temporal causal modelling on large volume time-series data. The proposed learning algorithm is used to determine the causal story associated with churn in telecommunication industry and flight delay in airline industry. Our model identifies and quantifies the respective causal factors for unfavourable events churn and flight delay. IEEE

IEEE Transactions on Big Data

Temporal Causal Modelling on Large Volume Enterprise Data

Deep learning algorithms provide state-of-the-art results on a multitude of applications. However, it is also well established that they are highly vulnerable to adversarial perturbations. It is often believed that the solution to this vulnerability of deep learning systems must come from deep networks only. Contrary to this common understanding, in this article, we propose a non-deep learning approach that searches over a set of well-known image transforms such as Discrete Wavelet Transform and Discrete Sine Transform, and classifying the features with a support vector machine-based classifier. Existing deep networks-based defense have been proven ineffective against sophisticated adversaries, whereas image transformation-based solution makes a strong defense because of the non-differential nature, multiscale, and orientation filtering. The proposed approach, which combines the outputs of two transforms, efficiently generalizes across databases as well as different unseen attacks and combinations of both (i.e., cross-database and unseen noise generation CNN model). The proposed algorithm is evaluated on large scale databases, including object database (validation set of ImageNet) and face recognition (MBGC) database. The proposed detection algorithm yields at-least 84.2\% and 80.1\% detection accuracy under seen and unseen database test settings, respectively. Besides, we also show how the impact of the adversarial perturbation can be neutralized using a wavelet decomposition-based filtering method of denoising. The mitigation results with different perturbation methods on several image databases demonstrate the effectiveness of the proposed method.

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING

Image Transformation-Based Defense Against Adversarial Perturbation on Deep Learning Models

Accidental new born swapping, health-care tracking, and child-abduction cases are some of the scenarios where new born face recognition can prove to be extremely useful. With the help of the right biometric system in place, cases of swapping, for instance, can be evaluated much faster. In this chapter, we first discuss the various biometric modalities along with their advantages and limitations. We next discuss the face biometrics in detail and present all the datasets available and existing hand-crafted, learning-based, as well as deep-learning-based techniques which have been proposed for new born face recognition. Finally, we evaluate and compare these techniques. Our comparative analysis shows that the state-of-the-art SSF-CNN technique achieves an average of rank-1 new born accuracy of 82.075 %. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Advances in Computer Vision and Pattern Recognition

Evolution of Newborn Face Recognition

Adversarial perturbations have demonstrated the vulnerabilities of deep learning algorithms to adversarial attacks. Existing adversary detection algorithms attempt to detect the singularities; however, they are in general, loss-function, database, or model dependent. To mitigate this limitation, we propose DAMAD--a generalized perturbation detection algorithm which is agnostic to model architecture, training data set, and loss function used during training. The proposed adversarial perturbation detection algorithm is based on the fusion of autoencoder embedding and statistical texture features extracted from convolutional neural networks. The performance of DAMAD is evaluated on the challenging scenarios of cross-database, cross-attack, and cross-architecture training and testing along with traditional evaluation of testing on the same database with known attack and model. Comparison with state-of-the-art perturbation detection algorithms showcase the effectiveness of the proposed algorithm on six databases: ImageNet, CIFAR-10, Multi-PIE, MEDS, point and shoot challenge (PaSC), and MNIST. Performance evaluation with nearly a quarter of a million adversarial and original images and comparison with recent algorithms show the effectiveness of the proposed algorithm. IEEE

IEEE Transactions on Neural Networks and Learning Systems

DAMAD: Database, Attack, and Model Agnostic Adversarial Perturbation Detector

Person re-identification (re-ID) in first-person (egocentric) vision is a fairly new and unexplored problem. With the increase of wearable video recording devices, egocentric data becomes readily available, and person re-identification has the potential to benefit greatly from this. However, there is a significant lack of large scale structured egocentric datasets for person re-identification, due to the poor video quality and lack of individuals in most of the recorded content. Although a lot of research has been done in person re-identification based on fixed surveillance cameras, these do not directly benefit egocentric re-ID. Machine learning models trained on the publicly available large scale re-ID datasets cannot be applied to egocentric re-ID due to the dataset bias problem. The proposed algorithm makes use of neural style transfer (NST) that incorporates a variant of Convolutional Neural Network (CNN) to utilize the benefits of both fixed camera vision and first-person vision. NST generates images having features from both egocentric datasets and fixed camera datasets, that are fed through a VGG-16 network trained on a fixed-camera dataset for feature extraction. These extracted features are then used to re-identify individuals. The fixed camera dataset Market-1501 [20] and the first-person dataset EGO Re-ID [3] are applied for this work and the results are on par with the present re-identification models in the egocentric domain. © 2021, Springer Nature Singapore Pte Ltd.

Communications in Computer and Information Science

Domain Adaptive Egocentric Person Re-identification

Errors in a transmitted message is unavoidable since noise is inevitable in any communication channel. For reliable transmission of messages, the bit error rate has to be kept at an acceptable rate by the use of proper error control coding schemes. To ensure that the transmission is also secure, data encryption is used as an integral part of the system. This paper deals with the design and analysis of a secure and reliable communication system accomplished using logistic map-based chaotic encryption and turbo product codes. The system is simulated using MATLAB and it is shown that the use of encryption for secure communication does not degrade the system performance. The hardware design of the decoder is also done and verified in Verilog using the same set of vectors as obtained from the system simulation. BER performance was analyzed in all the different scenarios and the correctness of the design was established. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.