Partha Maji

16 papers A 1Journal 9Unranked 5
YearRankTypeTitle / Venue / Authors
2024 J jnl
Enabling ImageNet-Scale Deep Learning on MCUs for Accurate and Efficient Inference.
IEEE Internet Things J.
Sulaiman Sadiq, Jonathon S. Hare, Simon Craske, Partha Maji, Geoff V. Merrett
2022 — conf
TinyOps: ImageNet Scale Deep Learning on Microcontrollers.
CVPR Workshops
Sulaiman Sadiq, Jonathon S. Hare, Partha Maji, Simon Craske, Geoff V. Merrett
2021 J jnl
An Underexplored Dilemma between Confidence and Calibration in Quantized Neural Networks.
CoRR
Guoxuan Xia, Sangwon Ha, Tiago Azevedo, Partha Maji
2021 J jnl
On Efficient Uncertainty Estimation for Resource-Constrained Mobile Applications.
CoRR
Johanna Rock, Tiago Azevedo, René de Jong, Daniel Ruiz-Muñoz, Partha Maji
2021 J jnl
On the Effects of Quantisation on Model Uncertainty in Bayesian Neural Networks.
CoRR
Martin Ferianc, Partha Maji, Matthew Mattina, Miguel Rodrigues
2021 A conf
On the effects of quantisation on model uncertainty in Bayesian neural networks.
UAI
Martin Ferianc, Partha Maji, Matthew Mattina, Miguel Rodrigues
2021 J jnl
Stochastic-Shield: A Probabilistic Approach Towards Training-Free Adversarial Defense in Quantized CNNs.
CoRR
Lorena Qendro, Sangwon Ha, René de Jong, Partha Maji
2021 — conf
Towards Efficient Point Cloud Graph Neural Networks Through Architectural Simplification.
ICCVW
Shyam A. Tailor, René de Jong, Tiago Azevedo, Matthew Mattina, Partha Maji
2021 J jnl
Towards Efficient Point Cloud Graph Neural Networks Through Architectural Simplification.
CoRR
Shyam A. Tailor, René de Jong, Tiago Azevedo, Matthew Mattina, Partha Maji
2020 — —
Model-architecture co-design of deep neural networks for embedded systems.
Partha Maji
2020 J jnl
Stochastic-YOLO: Efficient Probabilistic Object Detection under Dataset Shifts.
CoRR
Tiago Azevedo, René de Jong, Partha Maji
2019 — conf
Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUs.
EMC2@HPCA/CVPR/ISCA
Partha Maji, Andrew Mundy, Ganesh Dasika, Jesse G. Beu, Matthew Mattina, Robert Mullins
2019 J jnl
Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUs.
CoRR
Partha Maji, Andrew Mundy, Ganesh Dasika, Jesse G. Beu, Matthew Mattina, Robert Mullins
2018 J jnl
On the Reduction of Computational Complexity of Deep Convolutional Neural Networks.
Entropy
Partha Maji, Robert Mullins
2017 — conf
1D-FALCON: Accelerating Deep Convolutional Neural Network Inference by Co-optimization of Models and Underlying Arithmetic Implementation.
ICANN (2)
Partha Maji, Robert Mullins
2017 — conf
ADaPT: optimizing CNN inference on IoT and mobile devices using approximately separable 1-D kernels.
IML
Partha Maji, Daniel Bates, Alexandra W. Chadwick, Robert Mullins