arXiv subjects

Dinesh Bharadia

Publications and source records attributed to Dinesh Bharadia.

41 records · Page 3Linked to original sources

arXiv2021

SSLIDE: Sound Source Localization for Indoors based on Deep Learning

This paper presents SSLIDE, Sound Source Localization for Indoors using DEep learning, which applies deep neural networks (DNNs) with encoder-decoder structure to localize sound sources with random positions in a continuous space. The spatial features of sound signals received by each microphone are extracted and represented as likelihood surfaces for the sound source locations in each point. Our DNN consists of an encoder network followed by two decoders. The encoder obtains a compressed representation of the input likelihoods. One decoder resolves the multipath caused by reverberation, and the other decoder estimates the source location. Experiments based on both the simulated and experimental data show that our method can not only outperform multiple signal classification (MUSIC), steered response power with phase transform (SRP-PHAT), sparse Bayesian learning (SBL), and a competing convolutional neural network (CNN) approach in the reverberant environment but also achieve a good generalization performance.

eess.AS↗

arXiv2020

Sampling Training Data for Continual Learning Between Robots and the Cloud

Today's robotic fleets are increasingly measuring high-volume video and LIDAR sensory streams, which can be mined for valuable training data, such as rare scenes of road construction sites, to steadily improve robotic perception models. However, re-training perception models on growing volumes of rich sensory data in central compute servers (or the "cloud") places an enormous time and cost burden on network transfer, cloud storage, human annotation, and cloud computing resources. Hence, we introduce HarvestNet, an intelligent sampling algorithm that resides on-board a robot and reduces system bottlenecks by only storing rare, useful events to steadily improve perception models re-trained in the cloud. HarvestNet significantly improves the accuracy of machine-learning models on our novel dataset of road construction sites, field testing of self-driving cars, and streaming face recognition, while reducing cloud storage, dataset annotation time, and cloud compute time by between 65.7-81.3%. Further, it is between 1.05-2.58x more accurate than baseline algorithms and scalably runs on embedded deep learning hardware. We provide a suite of compute-efficient perception models for the Google Edge Tensor Processing Unit (TPU), an extended technical report, and a novel video dataset to the research community at https://sites.google.com/view/harvestnet.

cs.RO↗

arXiv2020

$S^3$Net: Semantic-Aware Self-supervised Depth Estimation with Monocular Videos and Synthetic Data

Solving depth estimation with monocular cameras enables the possibility of widespread use of cameras as low-cost depth estimation sensors in applications such as autonomous driving and robotics. However, learning such a scalable depth estimation model would require a lot of labeled data which is expensive to collect. There are two popular existing approaches which do not require annotated depth maps: (i) using labeled synthetic and unlabeled real data in an adversarial framework to predict more accurate depth, and (ii) unsupervised models which exploit geometric structure across space and time in monocular video frames. Ideally, we would like to leverage features provided by both approaches as they complement each other; however, existing methods do not adequately exploit these additive benefits. We present $S^3$Net, a self-supervised framework which combines these complementary features: we use synthetic and real-world images for training while exploiting geometric, temporal, as well as semantic constraints. Our novel consolidated architecture provides a new state-of-the-art in self-supervised depth estimation using monocular videos. We present a unique way to train this self-supervised framework, and achieve (i) more than $15\%$ improvement over previous synthetic supervised approaches that use domain adaptation and (ii) more than $10\%$ improvement over previous self-supervised approaches which exploit geometric constraints from the real data.

cs.CV↗

arXiv2019

SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception

Unsupervised learning for geometric perception (depth, optical flow, etc.) is of great interest to autonomous systems. Recent works on unsupervised learning have made considerable progress on perceiving geometry; however, they usually ignore the coherence of objects and perform poorly under scenarios with dark and noisy environments. In contrast, supervised learning algorithms, which are robust, require large labeled geometric dataset. This paper introduces SIGNet, a novel framework that provides robust geometry perception without requiring geometrically informative labels. Specifically, SIGNet integrates semantic information to make depth and flow predictions consistent with objects and robust to low lighting conditions. SIGNet is shown to improve upon the state-of-the-art unsupervised learning for depth prediction by 30% (in squared relative error). In particular, SIGNet improves the dynamic object class performance by 39% in depth prediction and 29% in flow prediction. Our code will be made available at https://github.com/mengyuest/SIGNet

cs.CV↗

arXiv2012

Lossy Compression of Quality Values via Rate Distortion Theory

Motivation: Next Generation Sequencing technologies revolutionized many fields in biology by enabling the fast and cheap sequencing of large amounts of genomic data. The ever increasing sequencing capacities enabled by current sequencing machines hold a lot of promise as for the future applications of these technologies, but also create increasing computational challenges related to the analysis and storage of these data. A typical sequencing data file may occupy tens or even hundreds of gigabytes of disk space, prohibitively large for many users. Raw sequencing data consists of both the DNA sequences (reads) and per-base quality values that indicate the level of confidence in the readout of these sequences. Quality values account for about half of the required disk space in the commonly used FASTQ format and therefore their compression can significantly reduce storage requirements and speed up analysis and transmission of these data. Results: In this paper we present a framework for the lossy compression of the quality value sequences of genomic read files. Numerical experiments with reference based alignment using these quality values suggest that we can achieve significant compression with little compromise in performance for several downstream applications of interest, as is consistent with our theoretical analysis. Our framework also allows compression in a regime - below one bit per quality value - for which there are no existing compressors.

q-bio.GN↗