Pabitra Mitra

Shubhi Shukla, Manaar Alam, Sarani Bhattacharya et al.

Recent Deep Learning (DL) advancements in solving complex real-world tasks have led to its widespread adoption in practical applications. However, this opportunity comes with significant underlying risks, as many of these models rely on privacy-sensitive data for training in a variety of applications, making them an overly-exposed threat surface for privacy violations. Furthermore, the widespread use of cloud-based Machine-Learning-as-a-Service (MLaaS) for its robust infrastructure support has broadened the threat surface to include a variety of remote side-channel attacks. In this paper, we first identify and report a novel data-dependent timing side-channel leakage (termed Class Leakage) in DL implementations originating from non-constant time branching operation in a widely used DL framework PyTorch. We further demonstrate a practical inference-time attack where an adversary with user privilege and hard-label black-box access to an MLaaS can exploit Class Leakage to compromise the privacy of MLaaS users. DL models are vulnerable to Membership Inference Attack (MIA), where an adversary's objective is to deduce whether any particular data has been used while training the model. In this paper, as a separate case study, we demonstrate that a DL model secured with differential privacy (a popular countermeasure against MIA) is still vulnerable to MIA against an adversary exploiting Class Leakage. We develop an easy-to-implement countermeasure by making a constant-time branching operation that alleviates the Class Leakage and also aids in mitigating MIA. We have chosen two standard benchmarking image classification datasets, CIFAR-10 and CIFAR-100 to train five state-of-the-art pre-trained DL models, over two different computing environments having Intel Xeon and Intel i7 processors to validate our approach.

Aravinda Reddy PN, K. Sreenivasa Rao, Raghavendra Ramachandra et al.

We present a novel face swapping method using the progressively growing structure of a pre-trained StyleGAN. Previous methods use different encoder decoder structures, embedding integration networks to produce high-quality results, but their quality suffers from entangled representation. We disentangle semantics by deriving identity and attribute features separately. By learning to map the concatenated features into the extended latent space, we leverage the state-of-the-art quality and its rich semantic extended latent space. Extensive experiments suggest that the proposed method successfully disentangles identity and attribute features and outperforms many state-of-the-art face swapping methods, both qualitatively and quantitatively.

Tapadyoti Banerjee, Pabitra Mitra, Dipanwita Roy Chowdhury

The advent of digital technologies has revolutionized traditional power distribution networks, transforming them into smart grids that are more reliable, efficient, and sustainable. Despite these advancements, electricity theft remains a significant threat to the effective operation of large electrical networks. To address this issue, we propose EnThM, a lightweight and communication-efficient scheme for real-time mitigation of power theft in smart grid systems. Our approach uses the hierarchical structure of the smart grid infrastructure to verify the authenticity of the metering data at multiple levels of the power distribution network. Our work focuses primarily on issues related to cryptographic security. The verification process involves statistically modeling the cumulative averages of the power usage data and applying rule-based checks on the aggregated power consumption at each level, while accounting for seasonal and daily consumption variations. The proposed method has been tested on benchmark consumption data, yielding high accuracy, efficient implementation, and real-time applicability.

Monnie Parida, Manjira Sinha, Anupam Basu et al.

This study aims to conduct an extensive detailed analysis of the Odia Braille reading comprehension among students with visual disability. Specifically, the study explores their reading speed and hand or finger movements. The study also aims to investigate any comprehension difficulties and reading errors they may encounter. Six students from the 9th and 10th grades, aged between 14 and 16, participated in the study. We observed participants hand movements to understand how reading errors were connected to hand movement and identify the students reading difficulties. We also evaluated the participants Odia Braille reading skills, including their reading speed (in words per minute), errors, and comprehension. The average speed of Odia Braille reader is 17.64wpm. According to the study, there was a noticeable correlation between reading speed and reading errors. As reading speed decreased, the number of reading errors tended to increase. Moreover, the study established a link between reduced Braille reading errors and improved reading comprehension. In contrast, the study found that better comprehension was associated with increased reading speed. The researchers concluded with some interesting findings about preferred Braille reading patterns. These findings have important theoretical, developmental, and methodological implications for instruction.

Nilanjan Sinhababu, Andrew Parry, Debasis Ganguly et al.

A supervised ranking model, despite its advantage of being effective, usually involves complex processing - typically multiple stages of task-specific pre-training and fine-tuning. This has motivated researchers to explore simpler pipelines leveraging large language models (LLMs) that are capable of working in a zero-shot manner. However, since zero-shot inference does not make use of a training set of pairs of queries and their relevant documents, its performance is mostly worse than that of supervised models, which are trained on such example pairs. Motivated by the existing findings that training examples generally improve zero-shot performance, in our work, we explore if this also applies to ranking models. More specifically, given a query and a pair of documents, the preference prediction task is improved by augmenting examples of preferences for similar queries from a training set. Our proposed pairwise few-shot ranker demonstrates consistent improvements over the zero-shot baseline on both in-domain (TREC DL) and out-domain (BEIR subset) retrieval benchmarks. Our method also achieves a close performance to that of a supervised model without requiring any complex training pipeline.

Argha Kamal Samanta, Harshika Goyal, Vasudha Joshi et al.

Diabetic retinopathy (DR) is a leading cause of preventable blindness worldwide, demanding accurate automated diagnostic systems. While general-domain vision-language models like Contrastive Language-Image Pre-Training (CLIP) perform well on natural image tasks, they struggle in medical domain applications, particularly in cross-modal retrieval for ophthalmological images. We propose a novel knowledge-enhanced joint embedding framework that integrates retinal fundus images, clinical text, and structured patient data through a multimodal transformer architecture to address the critical gap in medical image-text alignment. Our approach employs separate encoders for each modality: a Vision Transformer (ViT-B/16) for retinal images, Bio-ClinicalBERT for clinical narratives, and a multilayer perceptron for structured demographic and clinical features. These modalities are fused through a joint transformer with modality-specific embeddings, trained using multiple objectives including contrastive losses between modality pairs, reconstruction losses for images and text, and classification losses for DR severity grading according to ICDR and SDRG schemes. Experimental results on the Brazilian Multilabel Ophthalmological Dataset (BRSET) demonstrate significant improvements over baseline models. Our framework achieves near-perfect text-to-image retrieval performance with Recall@1 of 99.94% compared to fine-tuned CLIP's 1.29%, while maintaining state-of-the-art classification accuracy of 97.05% for SDRG and 97.97% for ICDR. Furthermore, zero-shot evaluation on the unseen DeepEyeNet dataset validates strong generalizability with 93.95% Recall@1 versus 0.22% for fine-tuned CLIP. These results demonstrate that our multimodal training approach effectively captures cross-modal relationships in the medical domain, establishing both superior retrieval capabilities and robust diagnostic performance.

Shubhi Shukla, Manaar Alam, Pabitra Mitra et al.

Machine learning, with its myriad applications, has become an integral component of numerous technological systems. A common practice in this domain is the use of transfer learning, where a pre-trained model's architecture, readily available to the public, is fine-tuned to suit specific tasks. As Machine Learning as a Service (MLaaS) platforms increasingly use pre-trained models in their backends, it's crucial to safeguard these architectures and understand their vulnerabilities. In this work, we present an approach based on the observation that the classification patterns of adversarial images can be used as a means to steal the models. Furthermore, the adversarial image classifications in conjunction with timing side channels can lead to a model stealing method. Our approach, designed for typical user-level access in remote MLaaS environments exploits varying misclassifications of adversarial images across different models to fingerprint several renowned Convolutional Neural Network (CNN) and Vision Transformer (ViT) architectures. We utilize the profiling of remote model inference times to reduce the necessary adversarial images, subsequently decreasing the number of queries required. We have presented our results over 27 pre-trained models of different CNN and ViT architectures using CIFAR-10 dataset and demonstrate a high accuracy of 88.8% while keeping the query budget under 20.

Aravinda Reddy PN, Raghavendra Ramachandra, Krothapalli Sreenivasa Rao et al.

Face-morphing attacks are a growing concern for biometric researchers, as they can be used to fool face recognition systems (FRS). These attacks can be generated at the image level (supervised) or representation level (unsupervised). Previous unsupervised morphing attacks have relied on generative adversarial networks (GANs). More recently, researchers have used linear interpolation of StyleGAN-encoded images to generate morphing attacks. In this paper, we propose a new method for generating high-quality morphing attacks using StyleGAN disentanglement. Our approach, called MLSD-GAN, spherically interpolates the disentangled latents to produce realistic and diverse morphing attacks. We evaluate the vulnerability of MLSD-GAN on two deep-learning-based FRS techniques. The results show that MLSD-GAN poses a significant threat to FRS, as it can generate morphing attacks that are highly effective at fooling these systems.

Nilanjan Sinhababu, Soumedhik Bharati, Debasis Ganguly et al.

Large Language Models (LLM) have been widely used in reranking. Computational overhead and large context lengths remain a challenging issue for LLM rerankers. Efficient reranking usually involves selecting a subset of the ranked list from the first stage, known as ranked list truncation (RLT). The truncated list is processed further by a reranker. For LLM rerankers, the ranked list is often partitioned and processed sequentially in batches to reduce the context length. Both these steps involve hyperparameters and topic-agnostic heuristics. Recently, LLMs have been shown to be effective for relevance judgment. Equivalently, we propose that LLMs can be used to generate reference documents that can act as a pivot between relevant and non-relevant documents in a ranked list. We propose methods to use these generated reference documents for RLT as well as for efficient listwise reranking. While reranking, we process the ranked list in either parallel batches of non-overlapping windows or overlapping windows with adaptive strides, improving the existing fixed stride setup. The generated reference documents are also shown to improve existing efficient listwise reranking frameworks. Experiments on TREC Deep Learning benchmarks show that our approach outperforms existing RLT-based approaches. In-domain and out-of-domain benchmarks demonstrate that our proposed methods accelerate LLM-based listwise reranking by up to 66\% compared to existing approaches. This work not only establishes a practical paradigm for efficient LLM-based reranking but also provides insight into the capability of LLMs to generate semantically controlled documents using relevance signals.

Aravinda Reddy PN, Raghavendra Ramachandra, K. Sreenivasa Rao et al.

In biometric systems, it is a common practice to associate each sample or template with a specific individual. Nevertheless, recent studies have demonstrated the feasibility of generating "morphed" biometric samples capable of matching multiple identities. These morph attacks have been recognized as potential security risks for biometric systems. However, most research on morph attacks has focused on biometric modalities that operate within the image domain, such as the face, fingerprints, and iris. In this work, we introduce Time-domain Voice Identity Morphing (TD-VIM), a novel approach for voice-based biometric morphing. This method enables the blending of voice characteristics from two distinct identities at the signal level, creating morphed samples that present a high vulnerability for speaker verification systems. Leveraging the Multilingual Audio-Visual Smartphone database, our study created four distinct morphed signals based on morphing factors and evaluated their effectiveness using a comprehensive vulnerability analysis. To assess the security impact of TD-VIM, we benchmarked our approach using the Generalized Morphing Attack Potential (G-MAP) metric, measuring attack success across two deep-learning-based Speaker Verification Systems (SVS) and one commercial system, Verispeak. Our findings indicate that the morphed voice samples achieved a high attack success rate, with G-MAP values reaching 99.40% on iPhone-11 and 99.74% on Samsung S8 in text-dependent scenarios, at a false match rate of 0.1%.

Aravinda Reddy PN, Raghavendra Ramachandra, Krothapalli Sreenivasa Rao et al.

Deepfakes are a major security risk for biometric authentication. This technology creates realistic fake videos that can impersonate real people, fooling systems that rely on facial features and voice patterns for identification. Existing multimodal deepfake detectors rely on conventional fusion methods, such as majority rule and ensemble voting, which often struggle to adapt to changing data characteristics and complex patterns. In this paper, we introduce the Straight-through Gumbel-Softmax (STGS) framework, offering a comprehensive approach to search multimodal fusion model architectures. Using a two-level search approach, the framework optimizes the network architecture, parameters, and performance. Initially, crucial features were efficiently identified from backbone networks, whereas within the cell structure, a weighted fusion operation integrated information from various sources. An architecture that maximizes the classification performance is derived by varying parameters such as temperature and sampling time. The experimental results on the FakeAVCeleb and SWAN-DF datasets demonstrated an impressive AUC value 94.4\% achieved with minimal model parameters.

Suryam Arnav Kalra, Arindam Biswas, Pabitra Mitra et al.

Expansion property of a graph refers to its strong connectivity as well as sparseness. It has been reported that deep neural networks can be pruned to a high degree of sparsity while maintaining their performance. Such pruning is essential for performing real time sequence learning tasks using recurrent neural networks in resource constrained platforms. We prune recurrent networks such as RNNs and LSTMs, maintaining a large spectral gap of the underlying graphs and ensuring their layerwise expansion properties. We also study the time unfolded recurrent network graphs in terms of the properties of their bipartite layers. Experimental results for the benchmark sequence MNIST, CIFAR-10, and Google speech command data show that expander graph properties are key to preserving classification accuracy of RNN and LSTM.

Manashi Chakraborty, Aritri Chakraborty, Prabir Kumar Biswas et al.

This paper presents a texture aware end-to-end trainable iris recognition system, specifically designed for datasets like iris having limited training data. We build upon our previous stagewise learning framework with certain key optimization and architectural innovations. First, we pretrain a Stage-1 encoder network with an unsupervised autoencoder learning optimized with an additional data relation loss on top of usual reconstruction loss. The data relation loss enables learning better texture representation which is pivotal for a texture rich dataset such as iris. Robustness of Stage-1 feature representation is further enhanced with an auxiliary denoising task. Such pre-training proves beneficial for effectively training deep networks on data constrained iris datasets. Next, in Stage-2 supervised refinement, we design a pairwise learning architecture for an end-to-end trainable iris recognition system. The pairwise learning includes the task of iris matching inside the training pipeline itself and results in significant improvement in recognition performance compared to usual offline matching. We validate our model across three publicly available iris datasets and the proposed model consistently outperforms both traditional and deep learning baselines for both Within-Dataset and Cross-Dataset configurations

Hareesh Mandalapu, Aravinda Reddy P N, Raghavendra Ramachandra et al.

Smartphones have been employed with biometric-based verification systems to provide security in highly sensitive applications. Audio-visual biometrics are getting popular due to their usability, and also it will be challenging to spoof because of their multimodal nature. In this work, we present an audio-visual smartphone dataset captured in five different recent smartphones. This new dataset contains 103 subjects captured in three different sessions considering the different real-world scenarios. Three different languages are acquired in this dataset to include the problem of language dependency of the speaker recognition systems. These unique characteristics of this dataset will pave the way to implement novel state-of-the-art unimodal or audio-visual speaker recognition systems. We also report the performance of the bench-marked biometric verification systems on our dataset. The robustness of biometric algorithms is evaluated towards multiple dependencies like signal noise, device, language and presentation attacks like replay and synthesized signals with extensive experiments. The obtained results raised many concerns about the generalization properties of state-of-the-art biometrics methods in smartphones.

Priyanka Sinha, Pabitra Mitra, Antonio Anastasio Bruto da Costa et al.

Multi-party dialogues are common in enterprise social media on technical as well as non-technical topics. The outcome of a conversation may be positive or negative. It is important to analyze why a dialogue ends with a particular sentiment from the point of view of conflict analysis as well as future collaboration design. We propose an explainable time series mining algorithm for such analysis. A dialogue is represented as an attributed time series of occurrences of keywords, EMPATH categories, and inferred sentiments at various points in its progress. A special decision tree, with decision metrics that take into account temporal relationships between dialogue events, is used for predicting the cause of the outcome sentiment. Interpretable rules mined from the classifier are used to explain the prediction. Experimental results are presented for the enterprise social media posts in a large company.

Hareesh Mandalapu, P N Aravinda Reddy, Raghavendra Ramachandra et al.

Biometric recognition is a trending technology that uses unique characteristics data to identify or verify/authenticate security applications. Amidst the classically used biometrics, voice and face attributes are the most propitious for prevalent applications in day-to-day life because they are easy to obtain through restrained and user-friendly procedures. The pervasiveness of low-cost audio and face capture sensors in smartphones, laptops, and tablets has made the advantage of voice and face biometrics more exceptional when compared to other biometrics. For many years, acoustic information alone has been a great success in automatic speaker verification applications. Meantime, the last decade or two has also witnessed a remarkable ascent in face recognition technologies. Nonetheless, in adverse unconstrained environments, neither of these techniques achieves optimal performance. Since audio-visual information carries correlated and complementary information, integrating them into one recognition system can increase the system's performance. The vulnerability of biometrics towards presentation attacks and audio-visual data usage for the detection of such attacks is also a hot topic of research. This paper made a comprehensive survey on existing state-of-the-art audio-visual recognition techniques, publicly available databases for benchmarking, and Presentation Attack Detection (PAD) algorithms. Further, a detailed discussion on challenges and open problems is presented in this field of biometrics.

Tianjian Huang, Prajwal Singhania, Maziar Sanjabi et al.

Quantization of the parameters of machine learning models, such as deep neural networks, requires solving constrained optimization problems, where the constraint set is formed by the Cartesian product of many simple discrete sets. For such optimization problems, we study the performance of the Alternating Direction Method of Multipliers for Quantization ($\texttt{ADMM-Q}$) algorithm, which is a variant of the widely-used ADMM method applied to our discrete optimization problem. We establish the convergence of the iterates of $\texttt{ADMM-Q}$ to certain $\textit{stationary points}$. To the best of our knowledge, this is the first analysis of an ADMM-type method for problems with discrete variables/constraints. Based on our theoretical insights, we develop a few variants of $\texttt{ADMM-Q}$ that can handle inexact update rules, and have improved performance via the use of "soft projection" and "injecting randomness to the algorithm". We empirically evaluate the efficacy of our proposed approaches.

Anirban Lahiri, Utanko Mitra, Sunreeta Sen et al.

A number of questionnaire based psychometric testing frameworks are globally for example OCEAN (Five factor) indicator, MBTI (Myers Brigg Type Indicator) etc. However, questionnaire based psychometric tests have some known shortcomings. This work explores whether these shortcomings can be mitigated through computer-based gaming platforms for evaluating psychometric parameters. A computer based psychometric game framework called Antarjami has been developed for evaluating OCEAN (Five factor) indicators. It investigates the feasibility of extracting psychometric parameters through computer-based games, utilizing underlying improvements in the area of modern artificial intelligence. The candidates for the test are subjected to a number scenarios as part of the computer based game and their reactions/responses are used to evaluate their psychometric parameters. As part of the study, the parameters obtained from the game were compared with those evaluated using paper based tests and scores given by a panel of psychologists. The achieved results were very promising.

Manashi Chakraborty, Mayukh Roy, Prabir Kumar Biswas et al.

In this paper, we present a texture aware lightweight deep learning framework for iris recognition. Our contributions are primarily three fold. Firstly, to address the dearth of labelled iris data, we propose a reconstruction loss guided unsupervised pre-training stage followed by supervised refinement. This drives the network weights to focus on discriminative iris texture patterns. Next, we propose several texture aware improvisations inside a Convolution Neural Net to better leverage iris textures. Finally, we show that our systematic training and architectural choices enable us to design an efficient framework with upto 100X fewer parameters than contemporary deep learning baselines yet achieve better recognition performance for within and cross dataset evaluations.

Anirban Santara, Rishabh Madan, Balaraman Ravindran et al.

In this work we present a novel approach for transfer-guided exploration in reinforcement learning that is inspired by the human tendency to leverage experiences from similar encounters in the past while navigating a new task. Given an optimal policy in a related task-environment, we show that its bisimulation distance from the current task-environment gives a lower bound on the optimal advantage of state-action pairs in the current task-environment. Transfer-guided Exploration (ExTra) samples actions from a Softmax distribution over these lower bounds. In this way, actions with potentially higher optimum advantage are sampled more frequently. In our experiments on gridworld environments, we demonstrate that given access to an optimal policy in a related task-environment, ExTra can outperform popular domain-specific exploration strategies viz. epsilon greedy, Model-Based Interval Estimation - Exploration Bonus (MBIE-EB), Pursuit and Boltzmann in rate of convergence. We further show that ExTra is robust to choices of source task and shows a graceful degradation of performance as the dissimilarity of the source task increases. We also demonstrate that ExTra, when used alongside traditional exploration algorithms, improves their rate of convergence. Thus it is capable of complementing the efficacy of traditional exploration algorithms.

Anirban Santara, Jayeeta Datta, Sourav Sarkar et al.

Hyperspectral images of land-cover captured by airborne or satellite-mounted sensors provide a rich source of information about the chemical composition of the materials present in a given place. This makes hyperspectral imaging an important tool for earth sciences, land-cover studies, and military and strategic applications. However, the scarcity of labeled training examples and spatial variability of spectral signature are two of the biggest challenges faced by hyperspectral image classification. In order to address these issues, we aim to develop a framework for material-agnostic information retrieval in hyperspectral images based on Positive-Unlabelled (PU) classification. Given a hyperspectral scene, the user labels some positive samples of a material he/she is looking for and our goal is to retrieve all the remaining instances of the query material in the scene. Additionally, we require the system to work equally well for any material in any scene without the user having to disclose the identity of the query material. This material-agnostic nature of the framework provides it with superior generalization abilities. We explore two alternative approaches to solve the hyperspectral image classification problem within this framework. The first approach is an adaptation of non-negative risk estimation based PU learning for hyperspectral data. The second approach is based on one-versus-all positive-negative classification where the negative class is approximately sampled using a novel spectral-spatial retrieval model. We propose two annotator models - uniform and blob - that represent the labelling patterns of a human annotator. We compare the performances of the proposed algorithms for each annotator model on three benchmark hyperspectral image datasets - Indian Pines, Pavia University and Salinas.

Debarghya China, Pabitra Mitra, Debdoot Sheet

Coronary artery disease accounts for a large number of deaths across the world and clinicians generally prefer using x-ray computed tomography or magnetic resonance imaging for localizing vascular pathologies. Interventional imaging modalities like intravascular ultrasound (IVUS) are used to adjunct diagnosis of atherosclerotic plaques in vessels, and help assess morphological state of the vessel and plaque, which play a significant role for treatment planning. Since speckle intensity in IVUS images are inherently stochastic in nature and challenge clinicians with accurate visibility of the vessel wall boundaries, it requires automation. In this paper we present a method for segmenting the lumen and external elastic laminae of the artery wall in IVUS images using random walks over a multiscale pyramid of Gaussian decomposed frames. The seeds for the random walker are initialized by supervised learning of ultrasonic backscattering and attenuation statistical mechanics from labelled training samples. We have experimentally evaluated the performance using $77$ IVUS images acquired at $40$ MHz that are available in the IVUS segmentation challenge dataset\footnote{http://www.cvc.uab.es/IVUSchallenge2011/dataset.html} to obtain a Jaccard score of $0.89 \pm 0.14$ for lumen and $0.85 \pm 0.12$ for external elastic laminae segmentation over a $10$-fold cross-validation study.

Sumanth Nandamuri, Debarghya China, Pabitra Mitra et al.

Ultrasound imaging is generally employed for real-time investigation of internal anatomy of the human body for disease identification. Delineation of the anatomical boundary of organs and pathological lesions is quite challenging due to the stochastic nature of speckle intensity in the images, which also introduces visual fatigue for the observer. This paper introduces a fully convolutional neural network based method to segment organ and pathologies in ultrasound volume by learning the spatial-relationship between closely related classes in the presence of stochastically varying speckle intensity. We propose a convolutional encoder-decoder like framework with (i) feature concatenation across matched layers in encoder and decoder and (ii) index passing based unpooling at the decoder for semantic segmentation of ultrasound volumes. We have experimentally evaluated the performance on publicly available datasets consisting of $10$ intravascular ultrasound pullback acquired at $20$ MHz and $16$ freehand thyroid ultrasound volumes acquired $11 - 16$ MHz. We have obtained a dice score of $0.93 \pm 0.08$ and $0.92 \pm 0.06$ respectively, following a $10$-fold cross-validation experiment while processing frame of $256 \times 384$ pixel in $0.035$s and a volume of $256 \times 384 \times 384$ voxel in $13.44$s.

Debarghya China, Francis Tom, Sumanth Nandamuri et al.

Ultrasound image compression by preserving speckle-based key information is a challenging task. In this paper, we introduce an ultrasound image compression framework with the ability to retain realism of speckle appearance despite achieving very high-density compression factors. The compressor employs a tissue segmentation method, transmitting segments along with transducer frequency, number of samples and image size as essential information required for decompression. The decompressor is based on a convolutional network trained to generate patho-realistic ultrasound images which convey essential information pertinent to tissue pathology visible in the images. We demonstrate generalizability of the building blocks using two variants to build the compressor. We have evaluated the quality of decompressed images using distortion losses as well as perception loss and compared it with other off the shelf solutions. The proposed method achieves a compression ratio of $725:1$ while preserving the statistical distribution of speckles. This enables image segmentation on decompressed images to achieve dice score of $0.89 \pm 0.11$, which evidently is not so accurately achievable when images are compressed with current standards like JPEG, JPEG 2000, WebP and BPG. We envision this frame work to serve as a roadmap for speckle image compression standards.

Sourav Pal, Tharun Mohandoss, Pabitra Mitra

The goal of our work is to use visual attention to enhance autonomous driving performance. We present two methods of predicting visual attention maps. The first method is a supervised learning approach in which we collect eye-gaze data for the task of driving and use this to train a model for predicting the attention map. The second method is a novel unsupervised approach where we train a model to learn to predict attention as it learns to drive a car. Finally, we present a comparative study of our results and show that the supervised approach for predicting attention when incorporated performs better than other approaches.

Avisek Lahiri, Arnav Jain, Prabir Kumar Biswas et al.

Contemporary benchmark methods for image inpainting are based on deep generative models and specifically leverage adversarial loss for yielding realistic reconstructions. However, these models cannot be directly applied on image/video sequences because of an intrinsic drawback- the reconstructions might be independently realistic, but, when visualized as a sequence, often lacks fidelity to the original uncorrupted sequence. The fundamental reason is that these methods try to find the best matching latent space representation near to natural image manifold without any explicit distance based loss. In this paper, we present a semantically conditioned Generative Adversarial Network (GAN) for sequence inpainting. The conditional information constrains the GAN to map a latent representation to a point in image manifold respecting the underlying pose and semantics of the scene. To the best of our knowledge, this is the first work which simultaneously addresses consistency and correctness of generative model based inpainting. We show that our generative model learns to disentangle pose and appearance information; this independence is exploited by our model to generate highly consistent reconstructions. The conditional information also aids the generator network in GAN to produce sharper images compared to the original GAN formulation. This helps in achieving more appealing inpainting performance. Though generic, our algorithm was targeted for inpainting on faces. When applied on CelebA and Youtube Faces datasets, the proposed method results in a significant improvement over the current benchmark, both in terms of quantitative evaluation (Peak Signal to Noise Ratio) and human visual scoring over diversified combinations of resolutions and deformations.

Anirban Santara, Kaustubh Mani, Pranoot Hatwar et al.

Deep learning based landcover classification algorithms have recently been proposed in literature. In hyperspectral images (HSI) they face the challenges of large dimensionality, spatial variability of spectral signatures and scarcity of labeled data. In this article we propose an end-to-end deep learning architecture that extracts band specific spectral-spatial features and performs landcover classification. The architecture has fewer independent connection weights and thus requires lesser number of training data. The method is found to outperform the highest reported accuracies on popular hyperspectral image data sets.

Arnav Kumar Jain, Abhinav Agarwalla, Kumar Krishna Agrawal et al.

In this paper, we introduce Key-Value Memory Networks to a multimodal setting and a novel key-addressing mechanism to deal with sequence-to-sequence models. The proposed model naturally decomposes the problem of video captioning into vision and language segments, dealing with them as key-value pairs. More specifically, we learn a semantic embedding (v) corresponding to each frame (k) in the video, thereby creating (k, v) memory slots. We propose to find the next step attention weights conditioned on the previous attention distributions for the key-value memory slots in the memory addressing schema. Exploiting this flexibility of the framework, we additionally capture spatial dependencies while mapping from the visual to semantic embedding. Experiments done on the Youtube2Text dataset demonstrate usefulness of recurrent key-addressing, while achieving competitive scores on BLEU@4, METEOR metrics against state-of-the-art models.

Avisek Lahiri, Sourya Roy, Anirban Santara et al.

Visual saliency detection tries to mimic human vision psychology which concentrates on sparse, important areas in natural image. Saliency prediction research has been traditionally based on low level features such as contrast, edge, etc. Recent thrust in saliency prediction research is to learn high level semantics using ground truth eye fixation datasets. In this paper we present, WEPSAM : Weakly Pre-Learnt Saliency Model as a pioneering effort of using domain specific pre-learing on ImageNet for saliency prediction using a light weight CNN architecture. The paper proposes a two step hierarchical learning, in which the first step is to develop a framework for weakly pre-training on a large scale dataset such as ImageNet which is void of human eye fixation maps. The second step refines the pre-trained model on a limited set of ground truth fixations. Analysis of loss on iSUN and SALICON datasets reveal that pre-trained network converges much faster compared to randomly initialized network. WEPSAM also outperforms some recent state-of-the-art saliency prediction models on the challenging MIT300 dataset.

Sourya Roy, Pabitra Mitra

In this paper we propose a Kalman filter aided saliency detection model which is based on the conjecture that salient regions are considerably different from our "visual expectation" or they are "visually surprising" in nature. In this work, we have structured our model with an immediate objective to predict saliency in static images. However, the proposed model can be easily extended for space-time saliency prediction. Our approach was evaluated using two publicly available benchmark data sets and results have been compared with other existing saliency models. The results clearly illustrate the superior performance of the proposed model over other approaches.

Biswajit Paria, Vikas Reddy, Anirban Santara et al.

The success of deep neural networks is mostly due their ability to learn meaningful features from the data. Features learned in the hidden layers of deep neural networks trained in computer vision tasks have been shown to be similar to mid-level vision features. We leverage this fact in this work and propose the visualization regularizer for image tasks. The proposed regularization technique enforces smoothness of the features learned by hidden nodes and turns out to be a special case of Tikhonov regularization. We achieve higher classification accuracy as compared to existing regularizers such as the L2 norm regularizer and dropout, on benchmark datasets without changing the training computational complexity.

Debapriya Maji, Anirban Santara, Pabitra Mitra et al.

Vision impairment due to pathological damage of the retina can largely be prevented through periodic screening using fundus color imaging. However the challenge with large scale screening is the inability to exhaustively detect fine blood vessels crucial to disease diagnosis. In this work we present a computational imaging framework using deep and ensemble learning for reliable detection of blood vessels in fundus color images. An ensemble of deep convolutional neural networks is trained to segment vessel and non-vessel areas of a color fundus image. During inference, the responses of the individual ConvNets of the ensemble are averaged to form the final segmentation. In experimental evaluation with the DRIVE database, we achieve the objective of vessel detection with maximum average accuracy of 94.7\% and area under ROC curve of 0.9283.

Anirban Santara, Debapriya Maji, DP Tejas et al.

Deep neural networks are capable of modelling highly non-linear functions by capturing different levels of abstraction of data hierarchically. While training deep networks, first the system is initialized near a good optimum by greedy layer-wise unsupervised pre-training. However, with burgeoning data and increasing dimensions of the architecture, the time complexity of this approach becomes enormous. Also, greedy pre-training of the layers often turns detrimental by over-training a layer causing it to lose harmony with the rest of the network. In this paper a synchronized parallel algorithm for pre-training deep networks on multi-core machines has been proposed. Different layers are trained by parallel threads running on different cores with regular synchronization. Thus the pre-training process becomes faster and chances of over-training are reduced. This is experimentally validated using a stacked autoencoder for dimensionality reduction of MNIST handwritten digit database. The proposed algorithm achieved 26\% speed-up compared to greedy layer-wise pre-training for achieving the same reconstruction accuracy substantiating its potential as an alternative.

Souradeep Chakraborty, Pabitra Mitra

We present an algorithm for graph based saliency computation that utilizes the underlying dense subgraphs in finding visually salient regions in an image. To compute the salient regions, the model first obtains a saliency map using random walks on a Markov chain. Next, k-dense subgraphs are detected to further enhance the salient regions in the image. Dense subgraphs convey more information about local graph structure than simple centrality measures. To generate the Markov chain, intensity and color features of an image in addition to region compactness is used. For evaluating the proposed model, we do extensive experiments on benchmark image data sets. The proposed method performs comparable to well-known algorithms in salient region detection.

Arindam Chaudhuri, Kajal De, Dipak Chatterjee et al.

Transportation Problem is an important problem which has been widely studied in Operations Research domain. It has been often used to simulate different real life problems. In particular, application of this Problem in NP Hard Problems has a remarkable significance. In this Paper, we present the closed, bounded and non empty feasible region of the transportation problem using fuzzy trapezoidal numbers which ensures the existence of an optimal solution to the balanced transportation problem. The multivalued nature of Fuzzy Sets allows handling of uncertainty and vagueness involved in the cost values of each cells in the transportation table. For finding the initial solution of the transportation problem we use the Fuzzy Vogel Approximation Method and for determining the optimality of the obtained solution Fuzzy Modified Distribution Method is used. The fuzzification of the cost of the transportation problem is discussed with the help of a numerical example. Finally, we discuss the computational complexity involved in the problem. To the best of our knowledge, this is the first work on obtaining the solution of the transportation problem using fuzzy trapezoidal numbers.