no code implementations • 28 Feb 2023 • Chintan Tundia, Rajiv Kumar, Om Damani, G. Sivakumar
In this paper, we introduce a publicly available object detection and instance segmentation (OD/IS) dataset for localizing farm ponds from aerial imagery.
1 code implementation • 28 Feb 2023 • Rajiv Kumar, G. Sivakumar
While single image methods can synthesize image samples with diversity, they do not model multiple images or capture the inherent relationship possible between two images.
no code implementations • 5 Jul 2022 • Bibin Wilson, Rajiv Kumar, Narayanarao Bhogapurapu, Anand Singh, Amit Sethi
DI-UNet uses a deep learning architecture to predict the resistivity using full polarimetric SAR data by promising a quick survey addition to the traditional method.
no code implementations • 30 Nov 2021 • Chintan Tundia, Rajiv Kumar, Om Damani, G. Sivakumar
Deep learning has led to many recent advances in object detection and instance segmentation, among other computer vision tasks.
1 code implementation • 9 Feb 2021 • Rajiv Kumar, Rishabh Dabral, G. Sivakumar
We assess the qualitative and quantitative results on image transfiguration, a cross-domain translation task, in a setting where the target domain shares similar semantics to the source domain.
Ranked #1 on Image-to-Image Translation on Zebra and Horses
no code implementations • 1 Mar 2019 • Arvind Kumar, Rajiv Kumar, Rajib Sarkar, S. Selvaraja
In this paper, we compute the regularity and Hilbert series of symbolic powers of the cover ideal of a graph $G$ when $G$ is either a crown graph or a complete multipartite graph.
Commutative Algebra 13D02, 13F20
no code implementations • 28 Nov 2018 • Robert Baraldi, Rajiv Kumar, Aleksandr Aravkin
These formulations are widely used, particularly for matrix completion and sparsity promotion in data interpolation and denoising.
no code implementations • 23 Apr 2018 • Michelle Liu, Rajiv Kumar, Eldad Haber, Aleksandr Aravkin
Stochastic optimization is key to efficient inversion in PDE-constrained optimization.
no code implementations • 9 Jul 2016 • Rajiv Kumar, Oscar López, Damek Davis, Aleksandr Y. Aravkin, Felix J. Herrmann
Acquisition cost is a crucial bottleneck for seismic workflows, and low-rank formulations for data interpolation allow practitioners to `fill in' data volumes from critically subsampled data acquired in the field.
no code implementations • 6 Jun 2013 • Kanika Bansal, Rajiv Kumar
In the present paper, a modified technique for noise removal named as K-Algorithm has been proposed, which has two stages as filtering and binarization.
no code implementations • 20 Feb 2013 • Aleksandr Y. Aravkin, Rajiv Kumar, Hassan Mansour, Ben Recht, Felix J. Herrmann
In this paper, we consider matrix completion formulations designed to hit a target data-fitting error level provided by the user, and propose an algorithm called LR-BPDN that is able to exploit factorized formulations to solve the corresponding optimization problem.