Machine learning in python: Main developments and technology trends in data science, machine learning, and artificial intelligence
Smarter applications are making better use of the insights gleaned from data, having an
impact on every industry and research discipline. At the core of this revolution lies the tools …
impact on every industry and research discipline. At the core of this revolution lies the tools …
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 …
The hardware lottery
S Hooker - Communications of the ACM, 2021 - dl.acm.org
The hardware lottery Page 1 58 COMMUNICATIONS OF THE ACM | DECEMBER 2021 | VOL.
64 | NO. 12 contributed articles IMA GE B Y ANDRIJ BOR YS A SSOCIA TE S HISTORY TELLS …
64 | NO. 12 contributed articles IMA GE B Y ANDRIJ BOR YS A SSOCIA TE S HISTORY TELLS …
Cnn filter db: An empirical investigation of trained convolutional filters
P Gavrikov, J Keuper - … of the IEEE/CVF conference on …, 2022 - openaccess.thecvf.com
Currently, many theoretical as well as practically relevant questions towards the
transferability and robustness of Convolutional Neural Networks (CNNs) remain unsolved …
transferability and robustness of Convolutional Neural Networks (CNNs) remain unsolved …
DECIMER. ai: an open platform for automated optical chemical structure identification, segmentation and recognition in scientific publications
The number of publications describing chemical structures has increased steadily over the
last decades. However, the majority of published chemical information is currently not …
last decades. However, the majority of published chemical information is currently not …
A full-stack search technique for domain optimized deep learning accelerators
The rapidly-changing deep learning landscape presents a unique opportunity for building
inference accelerators optimized for specific datacenter-scale workloads. We propose Full …
inference accelerators optimized for specific datacenter-scale workloads. We propose Full …
Fast and accurate single-image depth estimation on mobile devices, mobile ai 2021 challenge: Report
A Ignatov, G Malivenko, D Plowman… - Proceedings of the …, 2021 - openaccess.thecvf.com
Depth estimation is an important computer vision problem with many practical applications
to mobile devices. While many solutions have been proposed for this task, they are usually …
to mobile devices. While many solutions have been proposed for this task, they are usually …
Convolutional embedding makes hierarchical vision transformer stronger
Abstract Vision Transformers (ViTs) have recently dominated a range of computer vision
tasks, yet it suffers from low training data efficiency and inferior local semantic representation …
tasks, yet it suffers from low training data efficiency and inferior local semantic representation …
Efficient biomedical image segmentation on EdgeTPUs at point of care
AM Kist, M Döllinger - IEEE Access, 2020 - ieeexplore.ieee.org
The U-Net architecture is a state-of-the-art neural network for semantic image segmentation
that is widely used in biomedical research. It is based on an encoder-decoder framework …
that is widely used in biomedical research. It is based on an encoder-decoder framework …
YOLOv6-ESG: A lightweight seafood detection method
J Wang, Q Li, Z Fang, X Zhou, Z Tang, Y Han… - Journal of Marine …, 2023 - mdpi.com
The rapid development of convolutional neural networks has significant implications for
automated underwater fishing operations. Among these, object detection algorithms based …
automated underwater fishing operations. Among these, object detection algorithms based …