arXiv subjects

Gaurav Sharma

Publications and source records attributed to Gaurav Sharma.

At least 37 records · Page 2Linked to original sources

arXiv2023

OmniVec: Learning robust representations with cross modal sharing

Majority of research in learning based methods has been towards designing and training networks for specific tasks. However, many of the learning based tasks, across modalities, share commonalities and could be potentially tackled in a joint framework. We present an approach in such direction, to learn multiple tasks, in multiple modalities, with a unified architecture. The proposed network is composed of task specific encoders, a common trunk in the middle, followed by task specific prediction heads. We first pre-train it by self-supervised masked training, followed by sequential training for the different tasks. We train the network on all major modalities, e.g.\ visual, audio, text and 3D, and report results on $22$ diverse and challenging public benchmarks. We demonstrate empirically that, using a joint network to train across modalities leads to meaningful information sharing and this allows us to achieve state-of-the-art results on most of the benchmarks. We also show generalization of the trained network on cross-modal tasks as well as unseen datasets and tasks.

cs.CV↗

arXiv2023

Sentence Bag Graph Formulation for Biomedical Distant Supervision Relation Extraction

We introduce a novel graph-based framework for alleviating key challenges in distantly-supervised relation extraction and demonstrate its effectiveness in the challenging and important domain of biomedical data. Specifically, we propose a graph view of sentence bags referring to an entity pair, which enables message-passing based aggregation of information related to the entity pair over the sentence bag. The proposed framework alleviates the common problem of noisy labeling in distantly supervised relation extraction and also effectively incorporates inter-dependencies between sentences within a bag. Extensive experiments on two large-scale biomedical relation datasets and the widely utilized NYT dataset demonstrate that our proposed framework significantly outperforms the state-of-the-art methods for biomedical distant supervision relation extraction while also providing excellent performance for relation extraction in the general text mining domain.

cs.LG↗

arXiv2022

Role of Cybersecurity and Blockchain in Battlefield of Things

The Internet of Things is an essential component in the growth of an ecosystem that enables quick and precise judgments to be made for communication on the battleground. The usage of the battlefield of things (BoT) is, however, subject to several restrictions for a variety of reasons. There is a potential for instances of replay, data manipulation, breaches of privacy, and other similar occurrences. As a direct result of this, the implementation of a security mechanism to protect the communication that occurs within BoT has turned into an absolute requirement. To this aim, we propose a blockchain-based solution that is both safe and private for use in communications inside the BoT ecosystem. In addition, research is conducted on the benefits of integrating blockchain technology and cybersecurity into BoT application implementations. This work elaborates on the importance of integrating cybersecurity and blockchain-based tools, techniques and methodologies for BoT.

cs.CR↗

arXiv2022

Texture Representation via Analysis and Synthesis with Generative Adversarial Networks

We investigate data-driven texture modeling via analysis and synthesis with generative adversarial networks. For network training and testing, we have compiled a diverse set of spatially homogeneous textures, ranging from stochastic to regular. We adopt StyleGAN3 for synthesis and demonstrate that it produces diverse textures beyond those represented in the training data. For texture analysis, we propose GAN inversion using a novel latent domain reconstruction consistency criterion for synthesized textures, and iterative refinement with Gramian loss for real textures. We propose perceptual procedures for evaluating network capabilities, exploring the global and local behavior of latent space trajectories, and comparing with existing texture analysis-synthesis techniques.

cs.CV↗

arXiv2022

K-12BERT: BERT for K-12 education

Online education platforms are powered by various NLP pipelines, which utilize models like BERT to aid in content curation. Since the inception of the pre-trained language models like BERT, there have also been many efforts toward adapting these pre-trained models to specific domains. However, there has not been a model specifically adapted for the education domain (particularly K-12) across subjects to the best of our knowledge. In this work, we propose to train a language model on a corpus of data curated by us across multiple subjects from various sources for K-12 education. We also evaluate our model, K12-BERT, on downstream tasks like hierarchical taxonomy tagging.

cs.CL↗

arXiv2022

Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs

Label noise and long-tailed distributions are two major challenges in distantly supervised relation extraction. Recent studies have shown great progress on denoising, but paid little attention to the problem of long-tailed relations. In this paper, we introduce a constraint graph to model the dependencies between relation labels. On top of that, we further propose a novel constraint graph-based relation extraction framework(CGRE) to handle the two challenges simultaneously. CGRE employs graph convolution networks to propagate information from data-rich relation nodes to data-poor relation nodes, and thus boosts the representation learning of long-tailed relations. To further improve the noise immunity, a constraint-aware attention module is designed in CGRE to integrate the constraint information. Extensive experimental results indicate that CGRE achieves significant improvements over the previous methods for both denoising and long-tailed relation extraction. The pre-processed datasets and source code are publicly available at https://github.com/tmliang/CGRE.

cs.CL↗

arXiv2022

Discriminative Semantic Transitive Consistency for Cross-Modal Learning

Cross-modal retrieval is generally performed by projecting and aligning the data from two different modalities onto a shared representation space. This shared space often also acts as a bridge for translating the modalities. We address the problem of learning such representation space by proposing and exploiting the property of Discriminative Semantic Transitive Consistency -- ensuring that the data points are correctly classified even after being transferred to the other modality. Along with semantic transitive consistency, we also enforce the traditional distance minimizing constraint which makes the projections of the corresponding data points from both the modalities to come closer in the representation space. We analyze and compare the contribution of both the loss terms and their interaction, for the task. In addition, we incorporate semantic cycle-consistency for each of the modality. We empirically demonstrate better performance owing to the different components with clear ablation studies. We also provide qualitative results to support the proposals.

cs.CV↗

arXiv2022

Towards Universal Texture Synthesis by Combining Texton Broadcasting with Noise Injection in StyleGAN-2

We present a new approach for universal texture synthesis by incorporating a multi-scale texton broadcasting module in the StyleGAN-2 framework. The texton broadcasting module introduces an inductive bias, enabling generation of broader range of textures, from those with regular structures to completely stochastic ones. To train and evaluate the proposed approach, we construct a comprehensive high-resolution dataset that captures the diversity of natural textures as well as stochastic variations within each perceptually uniform texture. Experimental results demonstrate that the proposed approach yields significantly better quality textures than the state of the art. The ultimate goal of this work is a comprehensive understanding of texture space.

cs.CV↗

arXiv2021

Beyond Mono to Binaural: Generating Binaural Audio from Mono Audio with Depth and Cross Modal Attention

Binaural audio gives the listener an immersive experience and can enhance augmented and virtual reality. However, recording binaural audio requires specialized setup with a dummy human head having microphones in left and right ears. Such a recording setup is difficult to build and setup, therefore mono audio has become the preferred choice in common devices. To obtain the same impact as binaural audio, recent efforts have been directed towards lifting mono audio to binaural audio conditioned on the visual input from the scene. Such approaches have not used an important cue for the task: the distance of different sound producing objects from the microphones. In this work, we argue that depth map of the scene can act as a proxy for inducing distance information of different objects in the scene, for the task of audio binauralization. We propose a novel encoder-decoder architecture with a hierarchical attention mechanism to encode image, depth and audio feature jointly. We design the network on top of state-of-the-art transformer networks for image and depth representation. We show empirically that the proposed method outperforms state-of-the-art methods comfortably for two challenging public datasets FAIR-Play and MUSIC-Stereo. We also demonstrate with qualitative results that the method is able to focus on the right information required for the task. The project details are available at \url{https://krantiparida.github.io/projects/bmonobinaural.html}

cs.CV↗

arXiv2021

Depth Infused Binaural Audio Generation using Hierarchical Cross-Modal Attention

Binaural audio gives the listener the feeling of being in the recording place and enhances the immersive experience if coupled with AR/VR. But the problem with binaural audio recording is that it requires a specialized setup which is not possible to fabricate within handheld devices as compared to traditional mono audio that can be recorded with a single microphone. In order to overcome this drawback, prior works have tried to uplift the mono recorded audio to binaural audio as a post processing step conditioning on the visual input. But all the prior approaches missed other most important information required for the task, i.e. distance of different sound producing objects from the recording setup. In this work, we argue that the depth map of the scene can act as a proxy for encoding distance information of objects in the scene and show that adding depth features along with image features improves the performance both qualitatively and quantitatively. We propose a novel encoder-decoder architecture, where we use a hierarchical attention mechanism to encode the image and depth feature extracted from individual transformer backbone, with audio features at each layer of the decoder.

cs.SD↗

arXiv2021

Beyond Image to Depth: Improving Depth Prediction using Echoes

We address the problem of estimating depth with multi modal audio visual data. Inspired by the ability of animals, such as bats and dolphins, to infer distance of objects with echolocation, some recent methods have utilized echoes for depth estimation. We propose an end-to-end deep learning based pipeline utilizing RGB images, binaural echoes and estimated material properties of various objects within a scene. We argue that the relation between image, echoes and depth, for different scene elements, is greatly influenced by the properties of those elements, and a method designed to leverage this information can lead to significantly improved depth estimation from audio visual inputs. We propose a novel multi modal fusion technique, which incorporates the material properties explicitly while combining audio (echoes) and visual modalities to predict the scene depth. We show empirically, with experiments on Replica dataset, that the proposed method obtains 28% improvement in RMSE compared to the state-of-the-art audio-visual depth prediction method. To demonstrate the effectiveness of our method on larger dataset, we report competitive performance on Matterport3D, proposing to use it as a multimodal depth prediction benchmark with echoes for the first time. We also analyse the proposed method with exhaustive ablation experiments and qualitative results. The code and models are available at https://krantiparida.github.io/projects/bimgdepth.html

cs.CV↗

arXiv2021

Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks

We propose simple yet effective improvements in point representations and local neighborhood graph construction within the general framework of graph neural networks (GNNs) for 3D point cloud processing. As a first contribution, we propose to augment the vertex representations with important local geometric information of the points, followed by nonlinear projection using a MLP. As a second contribution, we propose to improve the graph construction for GNNs for 3D point clouds. The existing methods work with a k-nn based approach for constructing the local neighborhood graph. We argue that it might lead to reduction in coverage in case of dense sampling by sensors in some regions of the scene. The proposed methods aims to counter such problems and improve coverage in such cases. As the traditional GNNs were designed to work with general graphs, where vertices may have no geometric interpretations, we see both our proposals as augmenting the general graphs to incorporate the geometric nature of 3D point clouds. While being simple, we demonstrate with multiple challenging benchmarks, with relatively clean CAD models, as well as with real world noisy scans, that the proposed method achieves state of the art results on benchmarks for 3D classification (ModelNet40) , part segmentation (ShapeNet) and semantic segmentation (Stanford 3D Indoor Scenes Dataset). We also show that the proposed network achieves faster training convergence, i.e. ~40% less epochs for classification. The project details are available at https://siddharthsrivastava.github.io/publication/geomgcnn/

cs.CV↗

arXiv2020

Revisiting 70 years of lattice dynamics of BaTiO3: Combined first principle and experimental investigation

BaTiO3 is a classical ferroelectric studied for last one century for its ferroelectric properties. Lattice dynamics of BaTiO3 is crucial as the utility of devices is governed by phonons. In this work, we show that traditional characterization of the polar phonon modes is ambiguous and often misinterpreted. By combining Raman, Neutron and X-ray diffraction, dielectric spectroscopic observations with first principle calculations, we have re-examined the character of the normal modes of phonons of BaTiO3. We obtained Eigen displacements of vibrational modes through DFT calculations and reclassified the polar modes being Slater (Ti-O), Last (Ba-TiO3) and Axe (BO6) vibrations by correlating experimental and theoretical calculations. The study thus provides correct nomenclature of the polar modes along with the evidence of presence of short range polar distortions along (111) directions in all the phases shown by BaTiO3. The Burns temperature and absence of second order contributions have been witnessed in the temperature dependent Raman study.

cond-mat.mtrl-sci↗

arXiv2020

Object Detection with a Unified Label Space from Multiple Datasets

Given multiple datasets with different label spaces, the goal of this work is to train a single object detector predicting over the union of all the label spaces. The practical benefits of such an object detector are obvious and significant application-relevant categories can be picked and merged form arbitrary existing datasets. However, naive merging of datasets is not possible in this case, due to inconsistent object annotations. Consider an object category like faces that is annotated in one dataset, but is not annotated in another dataset, although the object itself appears in the latter images. Some categories, like face here, would thus be considered foreground in one dataset, but background in another. To address this challenge, we design a framework which works with such partial annotations, and we exploit a pseudo labeling approach that we adapt for our specific case. We propose loss functions that carefully integrate partial but correct annotations with complementary but noisy pseudo labels. Evaluation in the proposed novel setting requires full annotation on the test set. We collect the required annotations and define a new challenging experimental setup for this task based one existing public datasets. We show improved performances compared to competitive baselines and appropriate adaptations of existing work.

cs.CV↗

arXiv2020

A Novel Deep Learning Pipeline for Retinal Vessel Detection in Fluorescein Angiography

While recent advances in deep learning have significantly advanced the state of the art for vessel detection in color fundus (CF) images, the success for detecting vessels in fluorescein angiography (FA) has been stymied due to the lack of labeled ground truth datasets. We propose a novel pipeline to detect retinal vessels in FA images using deep neural networks that reduces the effort required for generating labeled ground truth data by combining two key components: cross-modality transfer and human-in-the-loop learning. The cross-modality transfer exploits concurrently captured CF and fundus FA images. Binary vessels maps are first detected from CF images with a pre-trained neural network and then are geometrically registered with and transferred to FA images via robust parametric chamfer alignment to a preliminary FA vessel detection obtained with an unsupervised technique. Using the transferred vessels as initial ground truth labels for deep learning, the human-in-the-loop approach progressively improves the quality of the ground truth labeling by iterating between deep-learning and labeling. The approach significantly reduces manual labeling effort while increasing engagement. We highlight several important considerations for the proposed methodology and validate the performance on three datasets. Experimental results demonstrate that the proposed pipeline significantly reduces the annotation effort and the resulting deep learning methods outperform prior existing FA vessel detection methods by a significant margin. A new public dataset, RECOVERY-FA19, is introduced that includes high-resolution ultra-widefield images and accurately labeled ground truth binary vessel maps.

cs.CV↗

arXiv2020

Imaging of Strain Driven Magnetic Domains and Strong Spin-Phonon Coupling in Epitaxial Thin Films of SrRuO3

Epitaxial thin films of SrRuO3 with large strain disorder were grown using pulsed laser deposition method which showed two distinct transition temperatures in Magnetic measurements. For the first time, we present visual evolution of magnetic domains across the two transitions using Magnetic force microscopy on these films. The study clearly showed that the magnetic anisotropy corresponding to the two transitions is different. It is observed that the perpendicular magnetic anisotropy is dominating in films which results in domain spin orientation preferably in out of plane direction. The Raman studies showed that the lattice is highly influenced by the magnetic order. The analysis of the phonon spectra around magnetic transition reveals the existence of strong spin-phonon coupling and the calculations resulted in spin-phonon coupling strength (λ) values of λ ~ 5 cm-1 and λ ~ 8.5 cm-1, for SrRuO3 films grown on LSAT and SrTiO3 single crystal substrates, respectively.

cond-mat.mtrl-sci↗

arXiv2019

Coordinated Joint Multimodal Embeddings for Generalized Audio-Visual Zeroshot Classification and Retrieval of Videos

We present an audio-visual multimodal approach for the task of zeroshot learning (ZSL) for classification and retrieval of videos. ZSL has been studied extensively in the recent past but has primarily been limited to visual modality and to images. We demonstrate that both audio and visual modalities are important for ZSL for videos. Since a dataset to study the task is currently not available, we also construct an appropriate multimodal dataset with 33 classes containing 156,416 videos, from an existing large scale audio event dataset. We empirically show that the performance improves by adding audio modality for both tasks of zeroshot classification and retrieval, when using multimodal extensions of embedding learning methods. We also propose a novel method to predict the `dominant' modality using a jointly learned modality attention network. We learn the attention in a semi-supervised setting and thus do not require any additional explicit labelling for the modalities. We provide qualitative validation of the modality specific attention, which also successfully generalizes to unseen test classes.

cs.CV↗

arXiv2019

Video Person Re-Identification using Learned Clip Similarity Aggregation

We address the challenging task of video-based person re-identification. Recent works have shown that splitting the video sequences into clips and then aggregating clip based similarity is appropriate for the task. We show that using a learned clip similarity aggregation function allows filtering out hard clip pairs, e.g. where the person is not clearly visible, is in a challenging pose, or where the poses in the two clips are too different to be informative. This allows the method to focus on clip-pairs which are more informative for the task. We also introduce the use of 3D CNNs for video-based re-identification and show their effectiveness by performing equivalent to previous works, which use optical flow in addition to RGB, while using RGB inputs only. We give quantitative results on three challenging public benchmarks and show better or competitive performance. We also validate our method qualitatively.

cs.CV↗