Vision-based holistic scene understanding towards proactive human–robot collaboration
Recently human–robot collaboration (HRC) has emerged as a promising paradigm for mass
personalization in manufacturing owing to the potential to fully exploit the strength of human …
personalization in manufacturing owing to the potential to fully exploit the strength of human …
Neural architecture search survey: A hardware perspective
KT Chitty-Venkata, AK Somani - ACM Computing Surveys, 2022 - dl.acm.org
We review the problem of automating hardware-aware architectural design process of Deep
Neural Networks (DNNs). The field of Convolutional Neural Network (CNN) algorithm design …
Neural Networks (DNNs). The field of Convolutional Neural Network (CNN) algorithm design …
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
CY Wang, A Bochkovskiy… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Real-time object detection is one of the most important research topics in computer vision.
As new approaches regarding architecture optimization and training optimization are …
As new approaches regarding architecture optimization and training optimization are …
Efficientnetv2: Smaller models and faster training
This paper introduces EfficientNetV2, a new family of convolutional networks that have faster
training speed and better parameter efficiency than previous models. To develop these …
training speed and better parameter efficiency than previous models. To develop these …
PP-PicoDet: A better real-time object detector on mobile devices
The better accuracy and efficiency trade-off has been a challenging problem in object
detection. In this work, we are dedicated to studying key optimizations and neural network …
detection. In this work, we are dedicated to studying key optimizations and neural network …
Multi-level feature interaction and efficient non-local information enhanced channel attention for image dehazing
Image dehazing is a challenging task in computer vision. Currently, most dehazing methods
adopt the U-Net architecture that directly fuses the decoding layer with the corresponding …
adopt the U-Net architecture that directly fuses the decoding layer with the corresponding …
Characterizing signal propagation to close the performance gap in unnormalized resnets
Batch Normalization is a key component in almost all state-of-the-art image classifiers, but it
also introduces practical challenges: it breaks the independence between training examples …
also introduces practical challenges: it breaks the independence between training examples …
Hw-nas-bench: Hardware-aware neural architecture search benchmark
HardWare-aware Neural Architecture Search (HW-NAS) has recently gained tremendous
attention by automating the design of DNNs deployed in more resource-constrained daily …
attention by automating the design of DNNs deployed in more resource-constrained daily …
A comprehensive survey on hardware-aware neural architecture search
Neural Architecture Search (NAS) methods have been growing in popularity. These
techniques have been fundamental to automate and speed up the time consuming and error …
techniques have been fundamental to automate and speed up the time consuming and error …
Vitcod: Vision transformer acceleration via dedicated algorithm and accelerator co-design
Vision Transformers (ViTs) have achieved state-of-the-art performance on various vision
tasks. However, ViTs' self-attention module is still arguably a major bottleneck, limiting their …
tasks. However, ViTs' self-attention module is still arguably a major bottleneck, limiting their …