Journal Article10.1007/S41745-019-0099-3
Beyond Supervised Learning: A Computer Vision Perspective
18
TL;DR: An overview of the contemporary literature surrounding alternatives to fully supervised learning in the deep learning context is provided and the relevant techniques that fall between the paradigm of supervised and unsupervised learning are summarized.
read more
Abstract: Fully supervised deep learning-based methods
have created a profound impact in various fields of computer science. Compared to classical methods, supervised deep learning-based techniques face scalability issues as they require huge amounts of labeled data and, more significantly, are unable to generalize to multiple domains and tasks. In recent years, a lot of research has been targeted towards addressing these issues within the deep learning community. Although there have been extensive surveys on learning paradigms such as semi-supervised and unsupervised learning, there are a few timely reviews after the emergence of deep learning. In this paper, we provide an overview of the contemporary literature surrounding alternatives to fully supervised learning in the deep learning context. First, we summarize the relevant techniques that fall between the paradigm of supervised and unsupervised learning. Second, we take autonomous navigation as a running example to explain and compare different models. Finally, we highlight some shortcomings of current methods and suggest future directions.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Book
Synthetic Data for Deep Learning
Sergey I. Nikolenko
- 26 Jun 2021
TL;DR: The synthetic-to-real domain adaptation problem that inevitably arises in applications of synthetic data is discussed, including synthetic- to-real refinement with GAN-based models and domain adaptation at the feature/model level without explicit data transformations.
391
A Review on Machine Learning Styles in Computer Vision—Techniques and Future Directions
01 Jan 2022
TL;DR: In this paper , different learning styles used in the field of Computer vision, Deep Learning, Neural Networks, and Machine Learning are discussed, and a literature analysis of how different machine learning styles evolved in Artificial Intelligence (AI) for computer vision is presented.
A Review on Machine Learning Styles in Computer Vision—Techniques and Future Directions
Supriya Mahadevkar,Bharti Khemani,Shruti Patil,Ketan Kotecha,Deepali Vora,Ajith Thomas Abraham,Lubna A. Gabralla +6 more
TL;DR: This paper presents literature analysis of how different machine learning styles evolved in the field of Artificial Intelligence (AI) for computer vision to help researchers working with learning styles as it gives a deep insight into future directions.
65
Improving Self-Organizing Maps with Unsupervised Feature Extraction
Lyes Khacef,Laurent Rodriguez,Benoit Miramond +2 more
- 18 Nov 2020
TL;DR: This work proposes to improve the SOM performance by using extracted features instead of raw data, and improves the SOM classification by +6.09\% and reach state-of-the-art performance on unsupervised image classification.
16
Beyond supervised learning in remote sensing: a systematic review of deep learning approaches
Benyamin Hosseiny,Masoud Mahdianpari,M. Hemati,Ali Radman,Fariba Mohammadimanesh,Jocelyn Chanussot +5 more
TL;DR: There is a sharp increasing trend in the applicability of NSDL methods during these few years particularly, with the advent of new deep architectures, such as adversarial, graph, and transformer models.
15
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
U-Net: Convolutional Networks for Biomedical Image Segmentation
Olaf Ronneberger,Philipp Fischer,Thomas Brox +2 more
- 05 Oct 2015
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TL;DR: This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.