no code implementations • 10 Apr 2024 • Bingyi Zhang, Rajgopal Kannan, Carl Busart, Viktor Prasanna
Moreover, GCV-Turbo supports the execution of the standalone CNNs or GNNs, achieving performance comparable to that of state-of-the-art CNN (GNN) accelerators for widely used CNN-only (GNN-only) models.
no code implementations • 6 Apr 2024 • Sachini Wickramasinghe, Dhruv Parikh, Bingyi Zhang, Rajgopal Kannan, Viktor Prasanna, Carl Busart
We directly train this model on SAR datasets which have limited training samples to evaluate its effectiveness for SAR ATR applications.
no code implementations • 21 Mar 2024 • Dhruv Parikh, Shouyi Li, Bingyi Zhang, Rajgopal Kannan, Carl Busart, Viktor Prasanna
For algorithm design, we systematically combine a hardware-aware structured block-pruning method for pruning model parameters and a dynamic token pruning method for removing unimportant token vectors.
1 code implementation • 1 Feb 2024 • Jacob Fein-Ashley, Tian Ye, Sachini Wickramasinghe, Bingyi Zhang, Rajgopal Kannan, Viktor Prasanna
Our experimental results on benchmark grayscale image datasets demonstrate the effectiveness of the proposed model, achieving vastly lower latency (up to 16$\times$ less) and competitive or leading performance compared to other state-of-the-art image classification models on various domain-specific grayscale image classification datasets.
Ranked #16 on Image Classification on Fashion-MNIST
no code implementations • 5 Jan 2024 • Sasindu Wijeratne, Bingyi Zhang, Rajgopal Kannan, Viktor Prasanna, Carl Busart
This detailed information includes the SAR image features that contributed to the classification, the classification confidence, and the probability of the identified object being classified as a different object type or class.
no code implementations • 4 Aug 2023 • Paul Chen, Pavan Manjunath, Sasindu Wijeratne, Bingyi Zhang, Viktor Prasanna
To exploit data sparsity during inference, we devise a runtime kernel mapping strategy that dynamically assigns computation tasks to the PL and AIE based on data sparsity.
no code implementations • 11 May 2023 • Bingyi Zhang, Sasindu Wijeratne, Rajgopal Kannan, Viktor Prasanna, Carl Busart
In this work, we propose a graph neural network (GNN) model to achieve accurate and low-latency SAR ATR.
no code implementations • 4 Jan 2023 • Bingyi Zhang, Rajgopal Kannan, Viktor Prasanna, Carl Busart
Compared with the state-of-the-art CNNs, the proposed GNN achieves comparable accuracy with $1/3258$ computation cost and $1/83$ model size.
1 code implementation • 10 Mar 2022 • Hongkuan Zhou, Bingyi Zhang, Rajgopal Kannan, Viktor Prasanna, Carl Busart
Taking advantage of the model optimizations, we propose a principled hardware architecture using batching, pipelining, and prefetching techniques to further improve the performance.