no code implementations • 5 Jul 2021 • Jaydeep Chauhan, Srikrishna Varadarajan, Muktabh Mayank Srivastava
We show that using unlabeled data with the noisy student training methodology, we can improve the state of the art on precise detection of objects in densely packed retail scenes.
no code implementations • 28 Dec 2020 • Jakob Suchan, Mehul Bhatt, Srikrishna Varadarajan
The method integrates state of the art in visual computing, and is developed as a modular framework that is generally usable within hybrid architectures for realtime perception and control.
1 code implementation • 19 Dec 2019 • Srikrishna Varadarajan, Sonaal Kant, Muktabh Mayank Srivastava
We train a standard object detector on a small, normally packed dataset with data augmentation techniques.
Ranked #1 on Object Detection on COCO 2017 (Mean mAP metric)
no code implementations • 31 May 2019 • Jakob Suchan, Mehul Bhatt, Srikrishna Varadarajan
We demonstrate the need and potential of systematically integrated vision and semantics} solutions for visual sensemaking (in the backdrop of autonomous driving).
no code implementations • 22 Aug 2018 • Pranaydeep Singh, Srikrishna Varadarajan, Ankit Narayan Singh, Muktabh Mayank Srivastava
We try to address the problem of document layout understanding using a simple algorithm which generalizes across multiple domains while training on just few examples per domain.
no code implementations • 19 Mar 2018 • Srikrishna Varadarajan, Muktabh Mayank Srivastava
We enhance the FCN output mask into final output bounding boxes by a Convolutional Encoder-Decoder (ConvAE) viz.
no code implementations • 20 Nov 2017 • Muktabh Mayank Srivastava, Pratyush Kumar, Lalit Pradhan, Srikrishna Varadarajan
We develop a Computer Aided Diagnosis (CAD) system, which enhances the performance of dentists in detecting wide range of dental caries.
no code implementations • 25 Oct 2017 • Srikrishna Varadarajan, Muktabh Mayank Srivastava, Monika Grewal, Pulkit Kumar
This work is an endeavor to develop a deep learning methodology for automated anatomical labeling of a given region of interest (ROI) in brain computed tomography (CT) scans.
no code implementations • 13 Oct 2017 • Monika Grewal, Muktabh Mayank Srivastava, Pulkit Kumar, Srikrishna Varadarajan
Further, the model utilizes 3D context from neighboring slices to improve predictions at each slice and subsequently, aggregates the slice-level predictions to provide diagnosis at CT level.