Partha Maji

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 15

Top Topics

Convolutional Neural Networks

Mobile Applications

Efficient Inference

Top Venues

IEEE Internet Things J.

Publications

Sulaiman Sadiq, Jonathon S. Hare, Simon Craske, Partha Maji, Geoff V. Merrett
Enabling ImageNet-Scale Deep Learning on MCUs for Accurate and Efficient Inference. IEEE Internet Things J. 11 (7) (2024)
Sulaiman Sadiq, Jonathon S. Hare, Partha Maji, Simon Craske, Geoff V. Merrett
TinyOps: ImageNet Scale Deep Learning on Microcontrollers. CVPR Workshops (2022)
Lorena Qendro, Sangwon Ha, René de Jong, Partha Maji
Stochastic-Shield: A Probabilistic Approach Towards Training-Free Adversarial Defense in Quantized CNNs. CoRR (2021)
Shyam A. Tailor, René de Jong, Tiago Azevedo, Matthew Mattina, Partha Maji
Towards Efficient Point Cloud Graph Neural Networks Through Architectural Simplification. ICCVW (2021)
Shyam A. Tailor, René de Jong, Tiago Azevedo, Matthew Mattina, Partha Maji
Towards Efficient Point Cloud Graph Neural Networks Through Architectural Simplification. CoRR (2021)
Johanna Rock, Tiago Azevedo, René de Jong, Daniel Ruiz-Muñoz, Partha Maji
On Efficient Uncertainty Estimation for Resource-Constrained Mobile Applications. CoRR (2021)
Martin Ferianc, Partha Maji, Matthew Mattina, Miguel Rodrigues
On the Effects of Quantisation on Model Uncertainty in Bayesian Neural Networks. CoRR (2021)
Martin Ferianc, Partha Maji, Matthew Mattina, Miguel Rodrigues
On the effects of quantisation on model uncertainty in Bayesian neural networks. UAI (2021)
Guoxuan Xia, Sangwon Ha, Tiago Azevedo, Partha Maji
An Underexplored Dilemma between Confidence and Calibration in Quantized Neural Networks. CoRR (2021)
Tiago Azevedo, René de Jong, Partha Maji
Stochastic-YOLO: Efficient Probabilistic Object Detection under Dataset Shifts. CoRR (2020)
Partha Maji, Andrew Mundy, Ganesh Dasika, Jesse G. Beu, Matthew Mattina, Robert D. Mullins
Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUs. EMC2@HPCA/CVPR/ISCA (2019)
Partha Maji, Andrew Mundy, Ganesh Dasika, Jesse G. Beu, Matthew Mattina, Robert D. Mullins
Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUs. CoRR (2019)
Partha Maji, Robert D. Mullins
On the Reduction of Computational Complexity of Deep Convolutional Neural Networks. Entropy 20 (4) (2018)
Partha Maji, Daniel Bates, Alex Chadwick, Robert D. Mullins
ADaPT: optimizing CNN inference on IoT and mobile devices using approximately separable 1-D kernels. IML (2017)
Partha Maji, Robert D. Mullins
1D-FALCON: Accelerating Deep Convolutional Neural Network Inference by Co-optimization of Models and Underlying Arithmetic Implementation. ICANN (2) (2017)