检索结果-内蒙古大学图书馆

Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in Computer vision Tasks for Robotic Grasping on the Edge

学校读者我要写书评

暂无评论

Fast GraspNeXt: A Fast Self-Attention Neural Network Archite...

IEEE Computer Society Conference on Computer vision and Pattern Recognition Workshops (CVPRW)

作者： Alexander Wong Yifan Wu Saad Abbasi Saeejith Nair Yuhao Chen Mohammad Javad Shafiee Vision and Image Processing Research Group University of Waterloo Waterloo Artificial Intelligence Institute Waterloo ON DarwinAI Corp. Waterloo ON

Multi-task learning has shown considerable promise for improving the performance of deep learning-driven vision systems for the purpose of robotic grasping. However, high architectural and computational complexity can result in poor suitability for deployment on embedded devices that are typically leveraged in robotic arms for real-world manufacturing and warehouse environments. As such, the design of highly efficient multi-task deep neural network architectures tailored for computer vision tasks for robotic grasping on the edge is highly desired for widespread adoption in manufacturing environments. Motivated by this, we propose Fast GraspNeXt, a fast self-attention neural network architecture tailored for embedded multi-task learning in computer vision tasks for robotic grasping. To build Fast GraspNeXt, we leverage a generative network architecture search strategy with a set of architectural constraints customized to achieve a strong balance between multitask learning performance and embedded inference efficiency. Experimental results on the MetaGraspNet benchmark dataset show that the Fast GraspNeXt network design achieves the highest performance (average precision (AP), accuracy, and mean squared error (MSE)) across multiple computer vision tasks when compared to other efficient multi-task network architecture designs, while having only 17.8M parameters (about >5× smaller), 259 GFLOPs (as much as >5× lower) and as much as >3.15× faster on a NVIDIA Jetson TX2 embedded processor.

关键词：

GHN-QAT: Training Graph Hypernetworks to Predict Quantization-Robust Parameters of Unseen Limited Precision Neural Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yun, Stone Wong, Alexander Vision and Image Processing Research Group University of Waterloo Waterloo Artificial Intelligence Institute Waterloo Canada DarwinAI Corp. Waterloo Canada

Graph Hypernetworks (GHN) can predict the parameters of varying unseen CNN architectures with surprisingly good accuracy at a fraction of the cost of iterative optimization. Following these successes, preliminary research has explored the use of GHNs to predict quantization-robust parameters for 8-bit and 4-bit quantized CNNs. However, this early work leveraged full-precision float32 training and only quantized for testing. We explore the impact of quantization-aware training and/or other quantization-based training strategies on quantized robustness and performance of GHN predicted parameters for low-precision CNNs. We show that quantization-aware training can significantly improve quantized accuracy for GHN predicted parameters of 4-bit quantized CNNs and even lead to greater-than-random accuracy for 2-bit quantized CNNs. These promising results open the door for future explorations such as investigating the use of GHN predicted parameters as initialization for further quantized training of individual CNNs, further exploration of "extreme bitwidth" quantization, and mixed precision quantization schemes. © 2023, CC BY-SA.

关键词： Forecasting

REGION-LEVEL labELS IN ICE CHARTS CAN PRODUCE PIXEL-LEVEL SEGMENTATION FOR SEA ICE TYPES

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Patel, Muhammed Chen, Xinwei Xu, Linlin Chen, Yuhao Scott, K. Andrea Clausi, David A. Vision and Image Processing Lab Systems Design Engineering University of Waterloo Canada School of Marine Science and Engineering South China University of Technology China Department of Mechanical and Mechatronics Engineering University of Waterloo Canada

Fully supervised deep learning approaches have demonstrated impressive accuracy in sea ice classification, but their dependence on high-resolution labels presents a significant challenge due to the difficulty of obtaining such data. In response, our weakly supervised learning method provides a compelling alternative by utilizing lower-resolution regional labels from expert-annotated ice charts. This approach achieves exceptional pixel-level classification performance by introducing regional loss representations during training to measure the disparity between predicted and ice chart-derived sea ice type distributions. Leveraging the AI4Arctic Sea Ice Challenge Dataset, our method outperforms the fully supervised U-Net benchmark, the top solution of the AutoIce challenge, in both mapping resolution and class-wise accuracy, marking a significant advancement in automated operational sea ice mapping. © 2024, CC BY.

关键词： Sea ice

MGSO: Monocular Real-time Photometric SLAM with Efficient 3D Gaussian Splatting

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hu, Yan Song Abboud, Nicolas Ali, Muhammad Qasim Yang, Adam Srebrnjak Elhajj, Imad Asmar, Daniel Chen, Yuhao Zelek, John S. Vision and Image Processing Lab The Faculty of System Design Engineering The University of Waterloo 200 University Avenue West WaterlooON Canada Vision and Robotics Lab Maroun Semaan Faculty of Engineering and Architecture American University of Beirut Riad El Solh Beirut1107 2020 Lebanon

Real-time SLAM with dense 3D mapping is computationally challenging, especially on resource-limited devices. The recent development of 3D Gaussian Splatting (3DGS) offers a promising approach for real-time dense 3D reconstruction. However, existing 3DGS-based SLAM systems struggle to balance hardware simplicity, speed, and map quality. Most systems excel in one or two of the aforementioned aspects but rarely achieve all. A key issue is the difficulty of initializing 3D Gaussians while concurrently conducting SLAM. To address these challenges, we present Monocular GSO (MGSO), a novel real-time SLAM system that integrates photometric SLAM with 3DGS. Photometric SLAM provides dense structured point clouds for 3DGS initialization, accelerating optimization and producing more efficient maps with fewer Gaussians. As a result, experiments show that our system generates reconstructions with a balance of quality, memory efficiency, and speed that outperforms the state-of-the-art. Furthermore, our system achieves all results using RGB inputs. We evaluate the Replica, TUM-RGBD, and EuRoC datasets against current live dense reconstruction systems. Not only do we surpass contemporary systems, but experiments also show that we maintain our performance on laptop hardware, making it a practical solution for robotics, A/R, and other real-time applications. © 2024, CC BY-NC-SA.

关键词： SLAM robotics

Systematic Architectural Design of Scale Transformed Attention Condenser DNNs via Multi-Scale Class Representational Response Similarity Analysis

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hryniowski, Andrew Wong, Alexander Vision and Image Processing Research Group University of Waterloo Canada Waterloo Artificial Intelligence Institute WaterlooON Canada DarwinAI Corp. WaterlooON Canada

Self-attention mechanisms are commonly included in a convolutional neural networks to achieve an improved efficiency performance balance. However, adding self-attention mechanisms adds additional hyperparameters to tune for the application at hand. In this work we propose a novel type of DNN analysis called Multi-Scale Class Representational Response Similarity Analysis (ClassRepSim) which can be used to identify specific design interventions that lead to more efficient self-attention convolutional neural network architectures. Using insights grained from ClassRepSim we propose the Spatial Transformed Attention Condenser (STAC) module, a novel attention-condenser based self-attention module. We show that adding STAC modules to ResNet style architectures can result in up to a 1.6% increase in top-1 accuracy compared to vanilla ResNet models and up to a 0.5% increase in top-1 accuracy compared to SENet models on the imageNet64x64 dataset, at the cost of up to 1.7% increase in FLOPs and 2x the number of parameters. In addition, we demonstrate that results from ClassRepSim analysis can be used to select an effective parameterization of the STAC module resulting in competitive performance compared to an extensive parameter search. Copyright © 2023, The Authors. All rights reserved.

关键词： Convolutional neural networks

Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in Computer vision Tasks for Robotic Grasping on the Edge

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wong, Alexander Wu, Yifan Abbasi, Saad Nair, Saeejith Chen, Yuhao Shafiee, Mohammad Javad Vision and Image Processing Research Group University of Waterloo Canada Waterloo Artificial Intelligence Institute WaterlooON Canada DarwinAI Corp. WaterlooON Canada

关键词： Computer vision

NAS-NeRF: Generative Neural Architecture Search for Neural Radiance Fields

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Nair, Saeejith Chen, Yuhao Shafiee, Mohammad Javad Wong, Alexander Vision and Image Processing Research Group University of Waterloo Canada Waterloo Artificial Intelligence Institute WaterlooON Canada DarwinAI Corp. WaterlooON Canada

Neural radiance fields (NeRFs) enable high-quality novel view synthesis, but their high computational complexity limits deployability. While existing neural-based solutions strive for efficiency, they use one-size-fits-all architectures regardless of scene complexity. The same architecture may be unnecessarily large for simple scenes but insufficient for complex ones. Thus, there is a need to dynamically optimize the neural network component of NeRFs to achieve a balance between computational complexity and specific targets for synthesis quality. We introduce NAS-NeRF, a generative neural architecture search strategy that generates compact, scene-specialized NeRF architectures by balancing architecture complexity and target synthesis quality metrics. Our method incorporates constraints on target metrics and budgets to guide the search towards architectures tailored for each scene. Experiments on the Blender synthetic dataset show the proposed NAS-NeRF can generate architectures up to 5.74× smaller, with 4.19× fewer FLOPs, and 1.93× faster on a GPU than baseline NeRFs, without suffering a drop in SSIM. Furthermore, we illustrate that NAS-NeRF can also achieve architectures up to 23× smaller, with 22× fewer FLOPs, and 4.7× faster than baseline NeRFs with only a 5.3% average SSIM drop. Our source code is also made publicly available1 Copyright © 2023, The Authors. All rights reserved.

关键词： Computational complexity

DeepfakeArt Challenge: A Benchmark Dataset for Generative AI Art Forgery and Data Poisoning Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Aboutalebi, Hossein Mao, Dayou Fan, Rongqi Xu, Carol He, Chris Wong, Alexander Vision and Image Processing Research Group University of Waterloo Canada Waterloo Artificial Intelligence Institute Waterloo Canada DarwinAI Corp. Waterloo Canada

The tremendous recent advances in generative artificial intelligence techniques have led to significant successes and promise in a wide range of different applications ranging from conversational agents and textual content generation to voice and visual synthesis. Amid the rise in generative AI and its increasing widespread adoption, there has been significant growing concern over the use of generative AI for malicious purposes. In the realm of visual content synthesis using generative AI, key areas of significant concern has been image forgery (e.g., generation of images containing or derived from copyright content), and data poisoning (i.e., generation of adversarially contaminated images). Motivated to address these key concerns to encourage responsible generative AI, we introduce the DeepfakeArt Challenge, a large-scale challenge benchmark dataset designed specifically to aid in the building of machine learning algorithms for generative AI art forgery and data poisoning detection. Comprising of over 32,000 records across a variety of generative forgery and data poisoning techniques, each entry consists of a pair of images that are either forgeries / adversarially contaminated or not. Each of the generated images in the DeepfakeArt Challenge benchmark dataset 1 has been quality checked in a comprehensive manner. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

DVQI: A Multi-task, Hardware-integrated Artificial Intelligence System for Automated Visual Inspection in Electronics Manufacturing

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chung, Audrey G. Li, Francis Ward, Jeremy Hryniowski, Andrew Wong, Alexander DarwinAI Corp. WaterlooON Canada Vision and Image Processing Research Group University of Waterloo Canada Waterloo Artificial Intelligence Institute WaterlooON Canada

As electronics manufacturers continue to face pressure to increase production efficiency amid difficulties with supply chains and labour shortages, many printed circuit board assembly (PCBA) manufacturers have begun to invest in automation and technological innovations to remain competitive. One such method is to leverage artificial intelligence (AI) to greatly augment existing manufacturing processes. In this paper, we present the DarwinAI Visual Quality Inspection (DVQI) system, a hardware-integration artificial intelligence system for the automated inspection of printed circuit board assembly defects in an electronics manufacturing environment. The DVQI system enables multi-task inspection via minimal programming and setup for manufacturing engineers while improving cycle time relative to manual inspection. We also present a case study of the deployed DVQI system’s performance and impact for a top electronics manufacturer. Copyright © 2023, The Authors. All rights reserved.

关键词： Production efficiency