Zobrazeno 1 - 10
of 182
pro vyhledávání: '"Shafiee, Mohammad Javad"'
We present DARLEI, a framework that combines evolutionary algorithms with parallelized reinforcement learning for efficiently training and evolving populations of UNIMAL agents. Our approach utilizes Proximal Policy Optimization (PPO) for individual
Externí odkaz:
http://arxiv.org/abs/2312.05171
Recent state-of-the-art semi-supervised Video Object Segmentation (VOS) methods have shown significant improvements in target object segmentation accuracy when information from preceding frames is used in segmenting the current frame. In particular,
Externí odkaz:
http://arxiv.org/abs/2309.15274
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
Externí odkaz:
http://arxiv.org/abs/2309.14293
Hockey rink registration is a useful tool for aiding and automating sports analysis. When combined with player tracking, it can provide location information of players on the rink by estimating a homography matrix that can warp broadcast video frames
Externí odkaz:
http://arxiv.org/abs/2401.01003
Autor:
Wong, Alexander, Wu, Yifan, Abbasi, Saad, Nair, Saeejith, Chen, Yuhao, Shafiee, Mohammad Javad
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 d
Externí odkaz:
http://arxiv.org/abs/2304.11196
Light guide plates are essential optical components widely used in a diverse range of applications ranging from medical lighting fixtures to back-lit TV displays. In this work, we introduce a fully-integrated, high-throughput, high-performance deep l
Externí odkaz:
http://arxiv.org/abs/2212.10632
With the growing adoption of deep learning for on-device TinyML applications, there has been an ever-increasing demand for efficient neural network backbones optimized for the edge. Recently, the introduction of attention condenser networks have resu
Externí odkaz:
http://arxiv.org/abs/2208.06980
Deep neural network (DNN) latency characterization is a time-consuming process and adds significant cost to Neural Architecture Search (NAS) processes when searching for efficient convolutional neural networks for embedded vision applications. DNN La
Externí odkaz:
http://arxiv.org/abs/2205.12660
Neural Architecture Search (NAS) has enabled automatic discovery of more efficient neural network architectures, especially for mobile and embedded vision applications. Although recent research has proposed ways of quickly estimating latency on unsee
Externí odkaz:
http://arxiv.org/abs/2204.12950
Light guide plates are essential optical components widely used in a diverse range of applications ranging from medical lighting fixtures to back-lit TV displays. An essential step in the manufacturing of light guide plates is the quality inspection
Externí odkaz:
http://arxiv.org/abs/2204.11765