61 citations · 112 across the 13 of their papers we have counts for
8 papers · 1 filter
OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages
Prem Selvaraj, Gokul NC, Pratyush Kumar +1
AI technologies for Natural Languages have made tremendous progress recently. However, commensurate progress has not been made on Sign Languages, in particular, in recognizing sign…
SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions
Vinod Ganesan, Gowtham Ramesh, Pratyush Kumar
Task-agnostic pre-training followed by task-specific fine-tuning is a default approach to train NLU models. Such models need to be deployed on devices across the cloud and the edge…
Machine Learning approaches to do size based reasoning on Retail Shelf objects to classify product variants
Muktabh Mayank Srivastava, Pratyush Kumar
There has been a surge in the number of Machine Learning methods to analyze products kept on retail shelves images. Deep learning based computer vision methods can be used to detec…
On the Prunability of Attention Heads in Multilingual BERT
Aakriti Budhraja, Madhura Pande, Pratyush Kumar +1
Large multilingual models, such as mBERT, have shown promise in crosslingual transfer. In this work, we employ pruning to quantify the robustness and interpret layer-wise importanc…
Design and Scaffolded Training of an Efficient DNN Operator for Computer Vision on the Edge
Vinod Ganesan, Pratyush Kumar
Massively parallel systolic arrays and resource-efficient depthwise separable convolutions are two promising techniques to accelerate DNN inference on the edge. Interestingly, thei…
FuSeConv: Fully Separable Convolutions for Fast Inference on Systolic Arrays
Surya Selvam, Vinod Ganesan, Pratyush Kumar
Both efficient neural networks and hardware accelerators are being explored to speed up DNN inference on edge devices. For example, MobileNet uses depthwise separable convolution t…