Abstract

Linear regression is a widely used technique to fit linear models and finds widespread applications across different areas of natural sciences, as well as field such as machine learning and statistics. In most real-world scenarios, however, linear regression problems are often ill-posed or the underlying model suffers from overfitting, leading to erroneous or trivial solutions. This is often dealt with by adding extra constraints, known as regularization. For instance, suppose that we are given N data points {(ai , bi)} N i=1 where ∀i : ai ∈ R d , ∀i : bi ∈ R. The assumption is that there is a vector x such that bi = x T ai +ei , where ei is a random variable (noise) with mean 0. Suppose A is the data matrix of dimension N × d, such that its i th row is the vector ai and b ∈ R N such that b = (b1, · · · , bN ) T . Adding an ℓ2-regularization, the objective is to obtain x that minimizes ∥Ax − b∥ 2 2 + λ∥Lx∥ 2 2 (0.0.1) where L is an appropriately chosen penalty matrix (or regularization matrix) of dimension N ×d and λ > 0 is the regularization parameter, an appropriately chosen constant. This regularization technique is known as general ℓ2 -regularization in the literature. It is a generalization of the well known ridge regression which corresponds to the case when L is the identity matrix. The closed-form solution of the general ℓ2-regularized ordinary least squares problem is given by x = A T A + λLTL
−1 A T b. (0.0.2) A straightforward observation is that even when AT A is singular, regularization ensures that the condition number (ratio of the maximum and the minimum singular values) of the resulting matrix is finite and therefore AT A + λLTL is invertible. Another observation is that when the condition number of A is arbitrarily large (the minimum singular value of A is arbitrarily small), the condition number of the matrix to be inverted in Equation 0.0.2 can be tamed significantly. Since the complexity of most quantum algorithms for the quantum versions of these problems depend the condition number, the complexity reduces significantly. These models can be generalized to situations where the data points are weighted or correlated which incorporate more realistic scenarios. Quantum linear systems solvers are possibly among the most studied quantum algorithms. In this work we develop the first quantum algorithms for ordinary, weighted and generalized least squares with generalized ℓ2- regularization. We assume access to (approximate) block-encodings of the relevant matrices and develop robust versions of quantum singular value transformations to implement linear transformations of these matrices. Our goal is to output a quantum state that is δ-close to |x⟩, the state encoding the solution to the underlying regularized least squares problem. Owing to the generality of the block-encoding framework, our algorithms are applicable to a variety of input models. In order to obtain our results, we work with approximate block-encodings of matrices and apply robust quantum singular value transformations (QSVT) to them. For most quantum linear algebra applications using QSVT, access to perfect block-encoding is assumed, and the robustness of such algorithms is left out. We develop a space-efficient variable time amplitude amplification (VTAA) procedure, which we then use in a variable-time matrix inversion algorithm. A crucial requirement for variable time matrix inversion algorithm is the application of the inversion procedure to the portion of the input state that is spanned by singular values larger than a certain threshold. In order to achieve this, prior results have made use of Gapped Phase Estimation (GPE), which is a simple variant of the standard phase estimation procedure. However, GPE requires extra registers that store the estimates of the phases, which are never used in the variable-time algorithm. In this work, instead of GPE, we make use of a robust version of quantum eigenvalue discrimination (QEVD) using QSVT, which decides whether the eigenvalue of a matrix is above or below a certain threshold without storing the eigenvalue estimates. Given the block-encoding of a matrix A with condition number κ, this procedure for implementing A+ reduces the number of additional qubits required for our variable time by a factor of O(log2 (κ/δ)) as compared to prior results, where δ is the desired accuracy. We show that in order to implement A+, the precision required in the block-encoding of A is determined in turn by the precision in the QEVD procedure. Consequently, this improves both variable-time amplitude amplification and quantum linear systems algorithm: we achieve optimal complexity (linear dependence in the condition number and polylogarithmic dependence on inverse-accuracy) using far fewer ancilla qubits. We then use this to develop our algorithms for ordinary, weighted and generali

Abstract

Agriculture is a vital area for the sustenance of humankind, engulfing manufacturing, security, traceability, and sustainable resource management. The agricultural industry has a major contribution to the economy due to its huge share in the gross domestic product (GDP) and as a source of employment. India is currently one of the world’s largest producers of agricultural products due to its bio-diversity. With the resources receding expeditiously, it is of utmost significance to innovate techniques that help in the subsistence of agriculture. The past few decades have seen immense change in the operation of the agricultural sector with the introduction of precision farming in conjunction with the Internet of Things (IoT). The growth of IoT and Blockchain technology as two rapidly emerging fields can ameliorate the state of the food chain today. The application of such advancements is highly based on an exchange of messages between various devices in the farming milieu and raises several scenarios which require cryptographic security. In this thesis, we understand the concept of precision agriculture, its evolution into smart agriculture, and the benefits of such evolution. The applications of IoT in agriculture, which give rise to various developing areas in agriculture, are studied. We study the security scenarios applicable in husbandry through the analysis of possible attacks and threats. The use and evolution of blockchain in the agriculture sector are studied. A layered architecture for smart farming is proposed that is independent of the underlying technologies, and the requirements of cryptographic security have been laid out based on the proposed architecture. A novel generalized blockchain-based security architecture has also been proposed. The testbeds available for IoT-based agricultural systems have been studied in detail. A literature survey of security protocols for various security subsectors in smart agriculture and authentication protocols in various smart applications provides a detailed dissection of the progress in each of the farming security sub-areas. We also perform a rigorous literature review to inspect the state-of-the-art information security using blockchain technology. The current progress in developing IoT-based tools and systems in the industry has also been studied. This research work proposes a series of authentication protocols that address the security issues concerning smart farming, including user authentication and mutual authentication between the various involved entities. The first contribution of this research work presents a new signature-based three-factor user authentication scheme in intelligent precision agriculture. The established session key between a user and the accessed smart device is then used to communicate securely to fetch real-time data from the device. The proposed scheme relies on one-way hashing and elliptic curve cryptography (ECC). For user biometric verification, the fuzzy extractor technique has been applied because it is verified using the Hamming distance to avoid false acceptance and rejection errors. A detailed security analysis, including the random-oracle-based formal security, formal security verification using the broadly-recognized Automated Validation of Internet Security Protocols and Applications (AVISPA) tool, and non-mathematical informal security analysis show the robustness of the proposed scheme against a number of potential attacks. In addition, testbed experiments are performed to measure the computational time of various cryptographic primitives used for comparative study among the proposed scheme and other competing schemes. The detailed comparative analysis shows that the proposed scheme has a better trade-off between its offered security and functionality features and communication and computational overheads compared to other competing schemes. In the second contribution of this thesis, new authentication and key management scheme for IoT-enabled Intelligent Precision Agriculture (IPA), called AKMS-AgriIoT, has been put forward with the private blockchain-based solution. Several IoT smart devices and drones can be deployed in an IPA to monitor an agricultural environment. The drones can be further utilized to collect the data from smart devices and send it to the Ground Station Server (GSS). However, insecure communication among the smart devices, drones, and the GSS make the IoT agriculture environment vulnerable to various potential attacks. The blocks formed with the encrypted transactions and their respective signatures by the GSS are mined by the cloud servers to verify and add the blocks to the private blockchain center. Detailed security analysis and comparative study reveal that the proposed AKMS-AgriIoT supports better security and provides more functionality features, fewer communication costs, and comparable computation costs compared to other relevant

Abstract

Handling fine-grained subtleties in text remains a challenge, despite the advances in the understanding and generation of textual content. The difficulties in the identification and segregation of such subtleties arises from the difficulty in sufficient human comprehension of these aspects and their implicit presence in the data used to train NLP models in understanding and generation tasks. In this thesis, we primarily focus on two types of such content: bias and clickbaits. Textual bias, which is implicitly manifested across corpora, arises from individual inclinations, perspectives and interpretations of facts and serves to distort the understanding of the information from the discourse by imposing subjective opinions. The presence of such affective content is a nuisance for encyclopedic platforms like Wikipedia that serve to provide knowledge from a neutral point of view and are used as a reliable source worldwide. Clickbaits are another form of malicious content that serve to distract user attention on social media websites. They usually work by luring a user to click on linked articles which often contain only trivial to no useful informational content in contrast to the intensity suggested by the “bait”, and result in unnecessary user frustration and potential masking of helpful information by diverting attention that could be paid to websites with objective information. While bias identification and mitigation have been well studied problems in NLP on the English language and there have been multiple definitions of bias from the perspectives of different corpora and objectives, we fix our definition from perspective of the neutral point of view on Wikipedia. Also, we seek to study the bias problem on a multilingual scale, dealing with native languages from the South Asian subcontinent as a study on low resource languages in conjunction with English. Prior to taking up these multilingual problems on the Wikipedia domain, we precede the same with a study of three different problems in this setting. In our first multilingual problem, we propose a novel architecture for fine-grained categorization of entities on a Wikipedia-based dataset of 30 languages. Following this, we set out to study two dual problems in a cross-lingual setting. In the first of these two, we aim at content enrichment in low resource languages making use of factual information from structured knowledge bases in English and explain the creation of a novel dataset for this study. In the other problem, we propose two methods for extraction of English facts from unstructured content in low resource languages with the aim of adequate utilization of the knowledge contained in such languages. A study of these three problems helped lay a solid foundation for the study of more subtle problems like bias on a multilingual scale. As a part of our study on bias identification and mitigation, we present several attempts at creating a sizeable multilingual, parallel dataset making use of edit tags on Wikipedia. We curate and propose our dataset for study which is based on translation from existing datasets in English. Following dataset creation, we present our modeling of the two problems of bias detection as a classification problem and bias mitigation as a style transfer problem through extensive experiments carried out in monolingual and multilingual settings. With the existing methods for evaluation of textual debiasing not sufficient for the purpose, we design an evaluation strategy combining traditional generation-based metrics with two additional metrics measuring the percentage of change and bias classification accuracy on the generated output. We also present several directions for extending this problem, following an analysis of our results. We approach the problem of mitigating the effects induced by a clickbait by looking at generation of “spoilers”, or short pieces of content to satisfy the curiosity generated by the clickbait. We attach the problem as a 2-stage pipeline, where the first stage predicts the type of spoiler that will be generated, and in the second stage, a spoiler type-specific spoiler generator extracts the necessary content from the article. We propose a novel Information Condensation-based modeling approach to tackle this problem, where we add filtering to the article associate with the clickbait, which helps wade out a lot of the potentially unnecessary information from the article. The article with condensed information is then used for the 2-stage problem. Our experiments reveal the merit of a contrastive learning-based method to design the filtering model, as opposed to simpler classification-based methods. We achieve SoTA results on the problem, and present an extensive analysis of our techniques used.

Abstract

Air pollution is a growing concern across the world. Long-term exposure to severe pollution can cause serious health issues. Outdoor air pollution accounts for an estimated 4.2 million deaths per year, primarily due to stroke, heart disease, lung cancer, and chronic respiratory diseases. Low and middleincome countries suffer the most, especially in the Western Pacific and South-East Asia regions. A significant cause of air pollution in urban areas worldwide is the high volume of road traffic. Studies have shown that people are willing to choose greener routes when credible information is provided One of the approaches to solve this problem is to design a transportation policy that balances multiple objectives of • Avoiding extreme pollution in any part of the road network • Enabling short transit times for the vehicles that follow the policy • Making effective use of the road capacities to route the traffic. We propose a novel sampling-based approach for this problem. We provide the first construction of a Markov Chain that can sample integer max flow solutions of a planar graph, with theoretical guarantees that the probabilities depend on the aggregate transit length. We designed a traffic policy using diverse samples and simulated traffic on real-world road maps using the SUMO traffic simulator. We designed the MaxFlow-MCMC algorithm that used the Markov Chain to sample max flow solutions and generate a k-optimal set. We observe a considerable decrease in areas with severe pollution when experimented with maps of large cities across the world compared to other approaches. Extending the above work, we also propose a significantly faster extension to the MaxFlow-MCMC algorithm without compromising on the performance involving the following contributions.We provide the first construction of a Markov Chain to sample a set of k-optimal max flow solutions directly from a planar graph. We also provide theoretical guarantees that the stationary distribution probabilities depend on both the k-optimality value and the aggregate transit length. We simulate traffic on large-scale realworld roadmaps using the SUMO traffic simulator. We observe a significant speed improvement in the range of 22 to 242 times in our experiments while obtaining lesser average pollution compared to the MaxFlow-MCMC algorithm. To summarize, we present two novel Markov Chain based algorithms to generate a diverse set of max flow solutions from a planar graph, while being scalable to large road networks. We provide theoretical guarantees for the Markov Chain and also provide simulation results to show that our algorithms perfomred better than existing algorithms.

Abstract

AI systems are ubiquitous in the current times, facilitating numerous real-world even real-time applications. Such sophistication is the consequence of advancement in algorith- mic research and concurrent up-gradation of computational resources. The existing models achieve near-optimal results for specific performance measures. Such perfection is often ob- tained at the cost of Fairness. By fairness, we try to quantify the impact an application has on an individual user (Individual Fairness) or a group of users (Group Fairness). In this work, we shift our focus from a single performance measure and explore the fairness of existing algorithms specifically in two settings, i) Fair resource allocation with strategic agents and ii) Fair classification models. We divide our work and discuss it in the following two parts. Part A – Fair Allocations with Strategic Agents. We consider the setting of resource allocation, where there are multiple items and multiple agents who have prefer- ences for these items. The agents are rational and strategic and may manipulate their preferences to obtain higher gains. The social planner must find allocations that satisfy certain desirable fairness properties and are resistant to manipulation, i.e. ensure strategy- proofnesss. Researchers have proposed algorithms that charge agents in order to prevent manipulations. However, analytically designing payments which are fair and strategy-proof is challenging. In this part, we propose data-driven approach to learn payments that are fair and strategy-proof. We additionally consider resource allocation settings wherein charging payments is not feasible. We analyze the existence of strategy-proof algorithms that ensure air allocations. We consider certain well known fairness notions like envy-freeness, pro- portionality and max-min share allocations. Such notions only ensure individual fairness of the agents involved. Part B – Fair Decisions for Groups. We consider machine learning-based classifi- cation algorithms. The accuracy of such algorithms has been the primary concern and is widely researched. More recently, researchers have uncovered the prejudiced predictions of such models towards certain demographic groups. Due to existing bias against certain race, gender or age, the data available is often biased. The prejudices in the data, amplified by the algorithms trained only for achieving higher accuracy, lead to unfair decisions to certain groups. Moreover, such algorithms made public on various online platforms poten- tially leak private information of the individual data used in training. Ensuring fairness and privacy in a machine learning framework gives rise to a non-convex and complex op- timization with multiple constraints. Towards this, we rely on learning-based approaches and exploit neural networks’ immense capacity to get closer to the goal.

Abstract

Speech is the most basic and reliable form of communication. In signal processing, speech signal carrying the message is represented in the form of an acoustic waveform. Having an insight into acoustics of speech contributes to production and perception robustness. One of the best means to study this is by exploiting the acoustic correlates of speech sounds. In this thesis, work mainly centers on introduction of acoustic correlates of vowels and their application in speech production, perception and analysis. Study of acoustic correlates of speech sounds brings out a rigorous introduction to acoustics of speech. Vowels are sonorants and the most audible sounds of speech. All the three works in this thesis mainly focus on studies related to vowel sounds and use formants as the basic spectral cue. Minor work has been extended to nasals in the first study. Formant bandwidth, one of the crucial acoustic correlates, was extracted for oral and nasal tracts using vowel and nasal articulations respectively. The exploitation of acoustic correlates of vowels against speech performance among different categories of gender was conducted in the second study. Here, the computed formants are utilized to construct vowel space area used for the comparison. Also, the role of source-filter was analyzed in perception of vowels. This study too incorporated formants in the vocal tract response of the LP method. Studying the acoustic correlates correlates of speech sounds would greatly enhance the knowledge on acoustical aspects of speech useful in Acoustic Phonetics, Auditory Phonetics, Speech Analysis, Speech Synthesis, Speech Signal Processing, to understand and evaluate speech signal.

Abstract

Text generation has shown tremendous promise recently, mainly attributed to the use of transformer architecture and the models pretrained on vast amounts of data. Multiple business scenarios today deploy neural-network-based models for natural language generation(NLG) tasks. However, this progress is limited to English and other high-resource(HR) languages, with NLG systems in low-resource(LR) languages far behind in terms of accuracy and fluency of generated text. This is due to several factors, such as lack of training data, lack of robust models supporting native script, and lack of linguistic resources as well. In this work, we extensively study an approach of cross-lingual NLG to tackle these challenges. Cross-lingual NLG implies exploiting the widely available data in HR language to generate the desired text in LR language. We focus on two significant tasks, i.e., fact-to-text and summarization, with a larger goal of generating Wikipedia article text in LR languages. We propose novel ways to build the datasets for the above tasks and also the approaches to generate text in LR languages. Firstly, we propose a novel task of cross-lingual fact-to-text generation(XF2T). Given the Wikidata facts in English, the system is expected to generate a sentence describing these facts in the desired language. To build a parallel dataset to train a model for the same, we explore several methods to link a fact from Wikidata to a sentence from Wikipedia, such as unsupervised, distantly supervised, and zero-shot learning-based approaches. We use the best approach to create the dataset XAlign of 0.55M instances across 12 Indian languages. Further, we implement transformer encoder-decoder and mT5 model as baselines using this dataset. In addition, we also explore the impact of task-specific pretraining, bilingual and monolingual models. We experiment with techniques to improve efficiency, such as structure-aware encoding of facts and fusing role-specific embeddings. We show that these approaches generate fluent and highly accurate sentences. Further, intending to generate longer text, we propose one more novel idea to generate the Wikipedia article section text using summarization. We leverage the citations available for each section on Wikipedia pages and build a parallel dataset for cross-lingual, multi-document, aspect-based summarization in 8 domains and 15 languages. In the first stage, i.e., extractive summarization, we aim to filter relevant sentences from a set of reference articles, for which we use saliency and graph-based methods. We experiment with recent SOTA models mT5 and mBART in the abstractive stage. Despite high noise in the input reference articles, we vi show that the system generates fluent and meaningful outputs. Although, in terms of content coverage and text coherency, models have a lot of scope for improvement. Overall, we work on various methods using cross-lingual NLG to advance the datasets and models in LR languages. We hope this work will boost more research in these critical areas in the future

Abstract

Language understanding has become crucial in different text classification tasks in Natural Language Processing (NLP) applications to get the desired output. Over the past decade, machine learning and deep learning algorithms have been evolving with efficient feature representations to give better results. The applications of NLP are becoming potent, domain, and language-specific. For resource-rich languages like English, the NLP applications give desired results due to the availability of large corpora, different kinds of annotated datasets, efficient feature representations, and tools. Due to the lack of large corpora and annotated datasets, many resource-poor Indian languages struggle to reap the benefits of deep feature representations. Moreover, adopting existing language models trained on large English corpora for Indian languages is often limited by data availability, rich morphological variation, syntax, and semantic differences. Most of the work being done in Indian languages is from a machine translation perspective. One solution is to use translation for re-creating datasets in low resource languages from English. But in case of Indian languages like Telugu, the meaning may change and some crucial information may be lost due to translation. This is because of their structural differences, morphological complexities, and semantic differences. In this thesis, our main objective is to mitigate the low-resource problem for Telugu. Overall, to accelerate NLP research in Telugu, we present several contributions: (1) A large Telugu raw corpus of 80,15,588 sentences (16,37,408 sentences from Telugu Wikipedia and 63,78,180 sentences crawled from different Telugu websites). (2) Annotated datasets in Telugu for sentiment analysis, emotion identification, hate speech detection, sarcasm identification, and clickbait detection. (3) For the Telugu corpus, we are the first to generate pre-trained distributed word and sentence embeddings such as Word2Vec-Te, GloVe-Te, FastText-Te, MetaEmbeddings-Te, Skip-Thought-Te. (8) We pre-trained different contextual language models for Telugu such as ELMo-Te, BERT-Te, RoBERTa-Te, ALBERT-Te, Electra-Te, and DistilBERT-Te, word and sentence embeddings using graph-based models: DeepWalk-Te and Node2Vec-Te, and Graph AutoEncoders (GAE). (4) We propose the multi-task learning model (MT-Text GCN) to reconstruct word-sentence graphs on TEL-NLP data while achieving multi-task text classification with learned graph embeddings. We show that our pre-trained embeddings are competitive or better than the existing multilingual pre-trained models: mBERT, XLM-R, and IndicBERT. Lastly, the fine-tuning of pre-trained models show higher performance than linear probing results on five NLP tasks. We also experiment with our pre-trained models on other NLP tasks available in Telugu (Named Entity Recognition, Article Genre Classification, Sentiment Analysis, and Summarization) and find that our Telugu pre-trained language models (BERT-Te and RoBERTa-Te) outperform the state-of-the-art system except for the sentiment task. We hope that the availability of the created resources for different NLP tasks will accelerate Telugu NLP research which has the potential to impact more than 85 million people. In this thesis, we aim at bridging the gap by creating resources for different NLP tasks in Telugu. These tasks can be extended to other Indian languages that are closer to Telugu culturally and linguistically by translating these resources without losing information like verb forms, cultural terms, vibhaktis etc. This is the first work that employs neural methods to Telugu language —a language that does not have good tools like NER, parsers and embeddings. Our work is the first attempt in this direction to provide good models in Telugu language by exploring different methods with available resources. It can also help the Telugu NLP community evaluate advances over more diverse tasks and applications. We open-source our corpus, five different annotated datasets (SA, EI, HS, SAR, and clickbait), lexicons, pre-trained embeddings, and code here1 . The pre-trained Transformer models for Telugu are available here2.

Abstract

Given a premise, the aim of Natural Language Inference is to identify a hypothesis as Entailed, Refuted, or Neutral. To do such classification, a model must acquire the ability to reason over the premise. While entailment tasks have been extensively studied with unstructured text as the premise, there is an increasing demand for learning to reason over semi-structured and organised data formats such as tables, knowledge graphs, databases, and combinations thereof. Structured data forms differ from unstructured text in the way they capture information and relationships – not just via language, but also through position and structure. Particularly, tables capture the connections between cells, which represent isolated distinct entities. Tabular data is organised so that items of the same kind are grouped together in rows, columns, or both. Consequently, it is straightforward to infer rankings, trends, unique items, and aggregate values from tabular data. These sorts of reasoning are specific to structured data formats, which makes inference on tables a difficult task requiring separate effort from inference on plain text. Creating challenging tabular inference data for supervision is necessary for mastering complex reasoning. Prior research in this sector has predominantly employed two data generating methodologies. The first technique is human annotation. This results in data that is inventive, fluent, and linguistically diverse. However, human annotation is costly and time-consuming, making it difficult to scale. The second form of data production is through synthetic means, where the data is generated using a defined set of rules or context-free grammar. This system is easily scalable in terms of both time and cost, but it lacks originality. Its results are predictable and adhere to predetermined patterns and fixed vocabulary. This research presents a framework for semi-automatically "recasting" existing tabular data in order to mitigate the drawbacks of both of the aforementioned data generation techniques. Existing data is perturbed, modified, and augmented through recasting to conform to the specifications of a given target task, which is Tabular Inference in this case. This framework is used to construct tabular NLI instances from five datasets that were originally designed for tasks such as table-to-text generation, tabular question answering, and tabular semantic parsing. To demonstrate the utility and quality of these datasets, this thesis explains how recasted data may be utilised as evaluation benchmarks and augmentation data to improve performance on tabular NLI tasks such as TabFact. In addition, this work evaluates the efficacy of models trained on recasted data in the zero-shot setting and examines performance trends across different types of recasted datasets. This thesis concludes with a discussion of the limitations and potential future paths of this field of study

Abstract

The reconstruction and analysis of 3D objects by computational systems has been an intensive and long-lasting research problem in the graphics and computer vision scientific communities. Traditional acquisition systems are largely restricted to studio environment setup which requires multiple synchronized and calibrated cameras. With the advent of active depth sensors like time-of-flight sensors, structured lighting sensors made 3D acquisition feasible. This advancement of technology has paved way to many research problems like 3D object localization, recognition, classification, reconstruction which demand innovating sophisticated/elegant solutions to match their ever growing applications. 3D human body reconstruction, in particular, has wider applications like virtual mirror, gait analysis, etc. Lately, with the advent of deep learning, 3D reconstruction from monocular images garnered significant interest among the research community as it can be applied to in-the-wild settings. Initially we started exploration of classification of 3D rigid objects due to availabilty of ShapeNet datasets. In this thesis, we propose an efficient characterization of 3D rigid objects which take local geometry features into consideration while constructing global features in the deep learning setup. We introduce learnable B-Spline surfaces in order to sense complex geometrical structures (large curvature variations). The locations of these surfaces are initialized over the voxel space and are learned during training phase leading to efficient classification performance. Later on, we primarily focus on rather challenging problem of non-rigid 3D human body reconstruction from monocular images. In this context, this thesis presents three principle approaches to address 3D reconstruction problem. Firstly, we propose a disentangled solution where we recover shape and texture of the 3D shape predicted using two different networks. We recover the volumetric shape of non-rigid human body shapes given a single view RGB image followed by orthographic texture view synthesis using the respective depth projection of the reconstructed (volumetric) shape and input RGB image. Secondly, we propose PeeledHuman - a novel shape representation of the human body that is robust to self-occlusions. PeeledHuman encodes the human body as a set of Peeled Depth and RGB maps in 2D, obtained by performing ray-tracing on the 3D body model and extending each ray beyond its first intersection. We learn these Peeled maps in an end-to-end generative adversarial fashion using our novel framework - PeelGAN. The PeelGAN enables us to predict shape and color of the 3D human in an end-to-end fashion at significantly low inference rates. Finally, we further improve PeelGAN by introducing a shape prior while reconstructing from monocular images. We propose a sparse and efficient fusion strategy to combine parametric body prior with a non-parametric PeeledHuman representation. The parametric body prior enforces geometrical consistency on the body shape and pose, while the non-parametric representation models loose clothing and handles self-occlusions as well. We also leverage the sparseness of the non-parametric representation for faster training of our network while using losses on 2D maps. We evaluate our proposed methods extensively on a number of datasets. In this thesis, we also introduce 3DHumans dataset, which is a 3D life-like dataset of human body scans with rich geometrical and textural details. We cover a wide variety of clothing styles ranging from loose robed clothing like saree to relatively tight-fitting shirt and trousers. The dataset consists of around 150 male and 50 unique female subjects. Total male scans are about 180 and female scans are around 70. In terms of regional diversity, for the first time, we capture body shape, appearance and clothing styles for the South-Asian population. This dataset will be released for research purposes.