Active learning at the imagenet scale

ZAS Emam, HM Chu, PY Chiang, W Czaja… - arxiv preprint arxiv …, 2021 - arxiv.org
Active learning (AL) algorithms aim to identify an optimal subset of data for annotation, such
that deep neural networks (DNN) can achieve better performance when trained on this …

Best practices in pool-based active learning for image classification

A Lang, C Mayer, R Timofte - 2021 - openreview.net
The recent popularity of active learning (AL) methods for image classification using deep-
learning has led to a large number of publications that lead to significant progress in the …

U-Net as a deep learning-based method for platelets segmentation in microscopic images

A Kumar, CA Coupland, TF Vaz, W Jones… - medRxiv, 2024 - medrxiv.org
Manual counting of platelets, in microscopy images, is greatly time-consuming. Our goal was
to automatically segment and count platelets images using a deep learning approach …

An obstacle detection system for automated guided vehicles

E Vähä - 2023 - osuva.uwasa.fi
The objective of this master's thesis is to investigate the utilization of computer vision and
object detection as an integral part of an automated guided vehicle's navigation system …

Active Learning at the ImageNet Scale

HM Chu, P Chiang, Z Emam, W Czaja, R Leapman… - openreview.net
Active learning (AL) algorithms aim to identify an optimal subset of data for annotation, such
that deep neural networks (DNN) can achieve better performance when trained on this …

Leveraging Transfer Learning Techniques for Transportation Infrastructure Image Classification: A Python-Based Approach with Xception Network

E Rukundo - Available at SSRN 4604205 - papers.ssrn.com
This article introduces transfer learning techniques using Python and the corresponding
libraries, focusing on transportation infrastructure image classification using the Keras …