[HTML][HTML] Review of image classification algorithms based on convolutional neural networks

L Chen, S Li, Q Bai, J Yang, S Jiang, Y Miao - Remote Sensing, 2021 - mdpi.com
Image classification has always been a hot research direction in the world, and the
emergence of deep learning has promoted the development of this field. Convolutional …

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 …

Visual transformers: Token-based image representation and processing for computer vision

B Wu, C Xu, X Dai, A Wan, P Zhang, Z Yan… - arxiv preprint arxiv …, 2020 - arxiv.org
Computer vision has achieved remarkable success by (a) representing images as uniformly-
arranged pixel arrays and (b) convolving highly-localized features. However, convolutions …

Searching for mobilenetv3

A Howard, M Sandler, G Chu… - Proceedings of the …, 2019 - openaccess.thecvf.com
We present the next generation of MobileNets based on a combination of complementary
search techniques as well as a novel architecture design. MobileNetV3 is tuned to mobile …

Dreaming to distill: Data-free knowledge transfer via deepinversion

H Yin, P Molchanov, JM Alvarez, Z Li… - Proceedings of the …, 2020 - openaccess.thecvf.com
We introduce DeepInversion, a new method for synthesizing images from the image
distribution used to train a deep neural network. We" invert" a trained network (teacher) to …

Single path one-shot neural architecture search with uniform sampling

Z Guo, X Zhang, H Mu, W Heng, Z Liu, Y Wei… - Computer Vision–ECCV …, 2020 - Springer
We revisit the one-shot Neural Architecture Search (NAS) paradigm and analyze its
advantages over existing NAS approaches. Existing one-shot method, however, is hard to …

Squeezesegv3: Spatially-adaptive convolution for efficient point-cloud segmentation

C Xu, B Wu, Z Wang, W Zhan, P Vajda… - Computer Vision–ECCV …, 2020 - Springer
LiDAR point-cloud segmentation is an important problem for many applications. For large-
scale point cloud segmentation, the de facto method is to project a 3D point cloud to get a …

Neural architecture search on imagenet in four gpu hours: A theoretically inspired perspective

W Chen, X Gong, Z Wang - arxiv preprint arxiv:2102.11535, 2021 - arxiv.org
Neural Architecture Search (NAS) has been explosively studied to automate the discovery of
top-performer neural networks. Current works require heavy training of supernet or intensive …

[HTML][HTML] Estimation of energy consumption in machine learning

E García-Martín, CF Rodrigues, G Riley… - Journal of Parallel and …, 2019 - Elsevier
Energy consumption has been widely studied in the computer architecture field for decades.
While the adoption of energy as a metric in machine learning is emerging, the majority of …

Fbnetv2: Differentiable neural architecture search for spatial and channel dimensions

A Wan, X Dai, P Zhang, Z He, Y Tian… - Proceedings of the …, 2020 - openaccess.thecvf.com
Abstract Differentiable Neural Architecture Search (DNAS) has demonstrated great success
in designing state-of-the-art, efficient neural networks. However, DARTS-based DNAS's …