no code implementations • 20 Nov 2023 • Farzad Salajegheh, Nader Asadi, Soroush Saryazdi, Sudhir Mudur
Our claim is that DAS's ability to pay increased attention to relevant features results in performance improvements when added to popular CNNs for Image Classification and Object Detection.
Ranked #1 on Object Detection on MSCOCO
no code implementations • 6 Oct 2023 • Tianhao Xie, Eugene Belilovsky, Sudhir Mudur, Tiberiu Popa
Direct mesh editing and deformation are key components in the geometric modeling and animation pipeline.
1 code implementation • CVPR 2023 • AmirMohammad Sarfi, Zahra Karimpour, Muawiz Chaudhary, Nasir M. Khalid, Mirco Ravanelli, Sudhir Mudur, Eugene Belilovsky
Our principal innovation in this work is to use Simulated annealing in EArly Layers (SEAL) of the network in place of re-initialization of later layers.
1 code implementation • 26 Mar 2023 • Nader Asadi, MohammadReza Davari, Sudhir Mudur, Rahaf Aljundi, Eugene Belilovsky
Class prototypes are evolved continually in the same latent space, enabling learning and prediction at any point.
no code implementations • CVPR 2022 • MohammadReza Davari, Nader Asadi, Sudhir Mudur, Rahaf Aljundi, Eugene Belilovsky
Continual Learning research typically focuses on tackling the phenomenon of catastrophic forgetting in neural networks.
no code implementations • 24 Mar 2022 • Nader Asadi, Sudhir Mudur, Eugene Belilovsky
Recent work studies the supervised online continual learning setting where a learner receives a stream of data whose class distribution changes over time.
no code implementations • 1 Aug 2018 • Serguei A. Mokhov, Miao Song, Jashanjot Singh, Joey Paquet, Mourad Debbabi, Sudhir Mudur
Visualization requirements in Forensic Lucid have to do with different levels of case knowledge abstraction, representation, aggregation, as well as the operational aspects as the final long-term goal of this proposal.
no code implementations • 6 Oct 2017 • Kaustubha Mendhurwar, Qing Gu, Vladimir de la Cruz, Sudhir Mudur, Tiberiu Popa
Action recognition, motion classification, gait analysis and synthesis are fundamental problems in a number of fields such as computer graphics, bio-mechanics and human computer interaction that generate a large body of research.
no code implementations • 21 Sep 2017 • Yuanlie He, Sudhir Mudur, Charalambos Poullis
In fact, for single-label object classification [i. e. only one object present in the image] the state-of-the-art techniques employ deep neural networks and are reporting very close to human-like performance.