Can Self-Supervised Representation Learning Methods Withstand Distribution Shifts and Corruptions?

1 code implementation • 31 Jul 2023 • Prakash Chandra Chhipa, Johan Rodahl Holmgren, Kanjar De, Rajkumar Saini, Marcus Liwicki

Detailed experiments have been conducted to study the robustness of self-supervised learning methods on distribution shifts and image corruptions.

Contrastive Learning Knowledge Distillation +2

Performance of data-driven inner speech decoding with same-task EEG-fMRI data fusion and bimodal models

no code implementations • 19 Jun 2023 • Holly Wilson, Scott Wellington, Foteini Simistira Liwicki, Vibha Gupta, Rajkumar Saini, Kanjar De, Nosheen Abid, Sumit Rakesh, Johan Eriksson, Oliver Watts, Xi Chen, Mohammad Golbabaee, Michael J. Proulx, Marcus Liwicki, Eamonn O'Neill, Benjamin Metcalfe

Decoding inner speech from the brain signal via hybridisation of fMRI and EEG data is explored to investigate the performance benefits over unimodal models.

EEG Feature Engineering

Nordic Vehicle Dataset (NVD): Performance of vehicle detectors using newly captured NVD from UAV in different snowy weather conditions

1 code implementation • 27 Apr 2023 • Hamam Mokayed, Amirhossein Nayebiastaneh, Kanjar De, Stergios Sozos, Olle Hagner, Bjorn Backe

This study aims to address this gap by providing the scientific community with data on vehicles captured by UAVs in different settings and under various snow cover conditions in the Nordic region.

Data Augmentation object-detection +1

Functional Knowledge Transfer with Self-supervised Representation Learning

1 code implementation • 12 Mar 2023 • Prakash Chandra Chhipa, Muskaan Chopra, Gopal Mengi, Varun Gupta, Richa Upadhyay, Meenakshi Subhash Chippa, Kanjar De, Rajkumar Saini, Seiichi Uchida, Marcus Liwicki

This work investigates the unexplored usability of self-supervised representation learning in the direction of functional knowledge transfer.

Representation Learning Self-Supervised Learning +1

Movie Recommendation System using Sentiment Analysis from Microblogging Data

1 code implementation • 27 Nov 2018 • Sudhanshu Kumar, Shirsendu Sukanta Halder, Kanjar De, Partha Pratim Roy

Traditional approaches in recommendation systems include collaborative filtering and content-based filtering.

Collaborative Filtering Movie Recommendation +2

Perceptual Conditional Generative Adversarial Networks for End-to-End Image Colourization

no code implementations • 27 Nov 2018 • Shirsendu Sukanta Halder, Kanjar De, Partha Pratim Roy

Colours are everywhere.