Zobrazeno 1 - 10
of 959
pro vyhledávání: '"Prasanna, Viktor"'
Edge computing's growing prominence, due to its ability to reduce communication latency and enable real-time processing, is promoting the rise of high-performance, heterogeneous System-on-Chip solutions. While current approaches often involve scaling
Externí odkaz:
http://arxiv.org/abs/2409.14803
Heterophilous graphs, where dissimilar nodes tend to connect, pose a challenge for graph neural networks (GNNs) as their superior performance typically comes from aggregating homophilous information. Increasing the GNN depth can expand the scope (i.e
Externí odkaz:
http://arxiv.org/abs/2409.06998
Attention mechanisms are critically important in the advancement of synthetic aperture radar (SAR) automatic target recognition (ATR) systems. Traditional SAR ATR models often struggle with the noisy nature of the SAR data, frequently learning from b
Externí odkaz:
http://arxiv.org/abs/2409.00473
Transformer based Large Language Models (LLMs) have recently reached state of the art performance in Natural Language Processing (NLP) and Computer Vision (CV) domains. LLMs use the Multi-Headed Self-Attention (MHSA) mechanism to capture long-range g
Externí odkaz:
http://arxiv.org/abs/2409.00287
Sparse Matricized Tensor Times Khatri-Rao Product (spMTTKRP) is the bottleneck kernel of sparse tensor decomposition. In this work, we propose a GPU-based algorithm design to address the key challenges in accelerating spMTTKRP computation, including
Externí odkaz:
http://arxiv.org/abs/2405.08470
Graph neural networks (GNNs) have recently empowered various novel computer vision (CV) tasks. In GNN-based CV tasks, a combination of CNN layers and GNN layers or only GNN layers are employed. This paper introduces GCV-Turbo, a domain-specific accel
Externí odkaz:
http://arxiv.org/abs/2404.07188
Convolutional Neural Networks (CNNs) have demonstrated remarkable ability throughout the field of computer vision. However, CNN inference requires a large number of arithmetic operations, making them expensive to deploy in hardware. Current approache
Externí odkaz:
http://arxiv.org/abs/2404.05872
Autor:
Wickramasinghe, Sachini, Parikh, Dhruv, Zhang, Bingyi, Kannan, Rajgopal, Prasanna, Viktor, Busart, Carl
Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) is a key technique used in military applications like remote-sensing image recognition. Vision Transformers (ViTs) are the current state-of-the-art in various computer vision applicati
Externí odkaz:
http://arxiv.org/abs/2404.04527
Deep Learning (DL) Models for Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR), while delivering improved performance, have been shown to be quite vulnerable to adversarial attacks. Existing works improve robustness by training model
Externí odkaz:
http://arxiv.org/abs/2404.03225
Adversarial attacks have demonstrated the vulnerability of Machine Learning (ML) image classifiers in Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) systems. An adversarial attack can deceive the classifier into making incorrect pr
Externí odkaz:
http://arxiv.org/abs/2403.18318