Madan Ravi Ganesh

Madan Ravi Ganesh

Computer Vision Research / Gamer / Gastronome

Publications

SNACS: Slimming Neural Networks Using Adaptive Connectivity Scores

Published in TNNLS (Under Review), 2021

SNACS advances the state-of-the-art in single shot neural network pruning by focusing on 3 key aspects of the pruning pipeline, 1) faster computation of connectivity scores, which determine the importance of a weight, 2) proposal of guidelines that automate the definition of the upper pruning percentage limits in all the layers of a neural network, and 3) identification of sensitivity as a priority measure to determine which weights are protected or pruned.

MINT: Deep Network Compression via Mutual Information-based Neuron Trimming

Published in ICPR, 2021

This project introduces the notion of using conditional mutual informationas a measure of dependence between neurons. The method, titled MINT. focuses on passing through a majority of information while retaining a small percentage of neurons between layers. Using only a single train-prune-retrain step, MINT is extremely competitive with commonly used DNN pruning baselines.

Rethinking Curriculum Learning with Incremental Labels and Adaptive Compensation

Published in BMVC, 2020

This work proposes a novel label-based curriculum learning algorithm called Learning with Incremental Labels and Adaptive Compensation. It emphasizes sample equality while incrementally learning labels and regularizes learning by adaptively modifying the target label vector. It performs label-based curriculum learning while surpassing performance from standard batch learning techniques.

A Geometric Approach to Online Streaming Feature Selection

Published in arXiv as Technical Report, 2020

This work revolves around the design of a state-of-the-art online streaming feature selection algorithm called Geometric Online Ap-proach which is fully functional when both features and samples are simultaneously streaming.

ViP: Video Platform for PyTorch

Published in arXiv as Technical Report, 2019

This project focused on the development of a pytorch-based video platform that can handle any image- or video-based application with minimal changes. It includes strong bookkeeping, mimics large mini-batch computations on lowmemory systems while including a large suite of video-specific preprocessing functions.