2 code implementations • 10 Mar 2023 • Ankit Manerikar, Avinash C. Kak
We propose a framework for the automatic one-shot segmentation of synthetic images generated by a StyleGAN.
no code implementations • 23 Feb 2023 • Rahul Deshmukh, Constantine J. Roros, Amith Kashyap, Avinash C. Kak
In our dataset, for each of the 60 AOIs that are meant for training, we augment the Planet datacube with temporally parallel datacubes of Landsat and Sentinel images.
no code implementations • 3 Jan 2022 • Constantine J. Roros, Avinash C. Kak
To overcome these difficulties, we developed the maskGRU framework that uses a weighted sum of the internal hidden state produced by a convGRU and a 3-channel mask of the tracked object's predicted bounding box as the hidden state to be used at the next time step of the underlying convGRU.
no code implementations • 10 Dec 2021 • Somrita Chattopadhyay, Avinash C. Kak
Our overall F1-score on DeepGlobe's challenging dataset is 0. 745.
no code implementations • 21 Feb 2021 • Rohan Sarkar, Avinash C. Kak
We present CheckSoft, a scalable event-driven software architecture for keeping track of people-object interactions in people-centric applications such as airport checkpoint security areas, automated retail stores, smart libraries, and so on.
1 code implementation • 24 Aug 2020 • Bharath Comandur, Avinash C. Kak
With no human supervision, our IoU scores for the buildings and roads classes are 0. 8 and 0. 64 respectively which are better than state-of-the-art approaches that use OSM labels and that are not completely automated.
no code implementations • 9 Jul 2019 • Sonali Patil, Bharath Comandur, Tanmay Prakash, Avinash C. Kak
Unlike the existing benckmarking datasets, we have also carried out a quantitative evaluation of our groundtruthed disparities using human annotated points in two of the AOIs.
no code implementations • 12 Nov 2018 • Ankit Manerikar, Tanmay Prakash, Avinash C. Kak
The computational effort for this fine-tuning for achieving a desired PD/PFA rate is far less than what it would take to create a new classifier with the same overall performance for the new set of threat specifications.