40 citations · 93 across the 31 of their papers we have counts for
6 papers · 1 filter
Rotation-Invariant Autoencoders for Signals on Spheres
Suhas Lohit, Shubhendu Trivedi
Omnidirectional images and spherical representations of shapes cannot be processed with conventional 2D convolutional neural networks (CNNs) as the unwrapping leads to large d…
Model Compression Using Optimal Transport
Suhas Lohit, Michael Jones
Model compression methods are important to allow for easier deployment of deep learning models in compute, memory and energy-constrained environments such as mobile phones. Knowled…
Multi-head Knowledge Distillation for Model Compression
Huan Wang, Suhas Lohit, Michael Jones +1
Several methods of knowledge distillation have been developed for neural network compression. While they all use the KL divergence loss to align the soft outputs of the student mod…
Recovering Trajectories of Unmarked Joints in 3D Human Actions Using Latent Space Optimization
Suhas Lohit, Rushil Anirudh, Pavan Turaga
Motion capture (mocap) and time-of-flight based sensing of human actions are becoming increasingly popular modalities to perform robust activity analysis. Applications range from a…
What Makes a "Good" Data Augmentation in Knowledge Distillation -- A Statistical Perspective
Huan Wang, Suhas Lohit, Mike Jones +1
Knowledge distillation (KD) is a general neural network training approach that uses a teacher model to guide the student model. Existing works mainly study KD from the network outp…
Generative Patch Priors for Practical Compressive Image Recovery
Rushil Anirudh, Suhas Lohit, Pavan Turaga
In this paper, we propose the generative patch prior (GPP) that defines a generative prior for compressive image recovery, based on patch-manifold models. Unlike learned, image-lev…