no code implementations • 28 May 2024 • Shubhang Bhatnagar, Narendra Ahuja
We present a novel, compositional DML model, inspired by electrostatic fields in physics that, instead of in tuples, represents the influence of each example (embedding) by a continuous potential field, and superposes the fields to obtain their combined global potential field.
no code implementations • 24 Apr 2024 • Samyak Rawlekar, Shubhang Bhatnagar, Vishnuvardhan Pogunulu Srinivasulu, Narendra Ahuja
Multi-label Recognition (MLR) involves the identification of multiple objects within an image.
no code implementations • 22 Mar 2024 • Shubhang Bhatnagar, Narendra Ahuja
For this purpose, we propose to model the high-dimensional data manifold using a piecewise-linear approximation, with each low-dimensional linear piece approximating the data manifold in a small neighborhood of a point.
no code implementations • 9 Aug 2023 • Shubhang Bhatnagar, Sharath Gopal, Narendra Ahuja, Liu Ren
We demonstrate the performance of our method on the LD-ConGR long-distance dataset where it outperforms previous state-of-the-art methods on recognition accuracy and compute efficiency.
no code implementations • 21 Oct 2021 • Himanshu Pradeep Aswani, Abhiraj Sunil Kanse, Shubhang Bhatnagar, Amit Sethi
Training CNNs from scratch on new domains typically demands large numbers of labeled images and computations, which is not suitable for low-power hardware.
no code implementations • 29 Oct 2020 • Shubhang Bhatnagar, Sachin Goyal, Darshan Tank, Amit Sethi
To counter the paucity of data, we also deploy another head on the scoring network for regularization via multi-task learning and use an unusual self-balancing hybrid scoring function.
no code implementations • 3 Dec 2018 • Ishan Bhatnagar, Shubhang Bhatnagar
We propose a novel algorithm for using Hopfield networks to denoise QR codes.