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 • 27 Mar 2024 • Tian Ye, Rajgopal Kannan, Viktor Prasanna, Carl Busart
Adversarial attacks have demonstrated the vulnerability of Machine Learning (ML) image classifiers in Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) systems.
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.
no code implementations • 13 Mar 2024 • Peihong Yu, Manav Mishra, Alec Koppel, Carl Busart, Priya Narayan, Dinesh Manocha, Amrit Bedi, Pratap Tokekar
Multi-Agent Reinforcement Learning (MARL) algorithms face the challenge of efficient exploration due to the exponential increase in the size of the joint state-action space.
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 • 12 Dec 2023 • Jacob Fein-Ashley, Tian Ye, Rajgopal Kannan, Viktor Prasanna, Carl Busart
Synthetic Aperture Radar SAR Automatic Target Recognition ATR is a key technique of remote-sensing image recognition which can be supported by deep neural networks The existing works of SAR ATR mostly focus on improving the accuracy of the target recognition while ignoring the systems performance in terms of speed and storage which is critical to real-world applications of SAR ATR For decision-makers aiming to identify a proper deep learning model to deploy in a SAR ATR system it is important to understand the performance of different candidate deep learning models and determine the best model accordingly This paper comprehensively benchmarks several advanced deep learning models for SAR ATR with multiple distinct SAR imagery datasets Specifically we train and test five SAR image classifiers based on Residual Neural Networks ResNet18 ResNet34 ResNet50 Graph Neural Network GNN and Vision Transformer for Small-Sized Datasets (SS-ViT) We select three datasets MSTAR GBSAR and SynthWakeSAR that offer heterogeneity We evaluate and compare the five classifiers concerning their classification accuracy runtime performance in terms of inference throughput and analytical performance in terms of number of parameters number of layers model size and number of operations Experimental results show that the GNN classifier outperforms with respect to throughput and latency However it is also shown that no clear model winner emerges from all of our chosen metrics and a one model rules all case is doubtful in the domain of SAR ATR
no code implementations • 5 Dec 2023 • Tian Ye, Rajgopal Kannan, Viktor Prasanna, Carl Busart, Lance Kaplan
Instead, adversarial attacks should be able to be implemented by physical actions, for example, placing additional false objects as scatterers around the on-ground target to perturb the SAR image and fool the SAR ATR.
no code implementations • 6 Nov 2023 • Kinjal Bhar, He Bai, Jemin George, Carl Busart
To demonstrate the efficacy of the proposed algorithm, we present simulations on a toy problem as well as on real world data sets to train ML models to perform classification tasks.
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 • 22 Apr 2023 • Wuxia Chen, Taposh Banerjee, Jemin George, Carl Busart
The proposed algorithm exploits a fundamental reward-detection trade-off present in these problems and uses a quickest change detection algorithm to detect the model change.
no code implementations • 14 Mar 2023 • Souradip Chakraborty, Kasun Weerakoon, Prithvi Poddar, Mohamed Elnoor, Priya Narayanan, Carl Busart, Pratap Tokekar, Amrit Singh Bedi, Dinesh Manocha
Reinforcement learning-based policies for continuous control robotic navigation tasks often fail to adapt to changes in the environment during real-time deployment, which may result in catastrophic failures.
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.
no code implementations • 16 Nov 2022 • Kinjal Bhar, He Bai, Jemin George, Carl Busart
We present a practical asynchronous data fusion model for networked agents to perform distributed Bayesian learning without sharing raw data.
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.
no code implementations • 9 Feb 2022 • Hasib-Al Rashid, Pretom Roy Ovi, Carl Busart, Aryya Gangopadhyay, Tinoosh Mohsenin
With the emergence of Artificial Intelligence (AI), new attention has been given to implement AI algorithms on resource constrained tiny devices to expand the application domain of IoT.