An overview of mixing augmentation methods and augmentation strategies
- URL: http://arxiv.org/abs/2107.09887v1
- Date: Wed, 21 Jul 2021 05:58:06 GMT
- Title: An overview of mixing augmentation methods and augmentation strategies
- Authors: Dominik Lewy and Jacek Ma\'ndziuk
- Abstract summary: This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017- 2021.
This survey focuses on two DA research streams: image mixing and automated selection of augmentation strategies.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Deep Convolutional Neural Networks have made an incredible progress in many
Computer Vision tasks. This progress, however, often relies on the availability
of large amounts of the training data, required to prevent over-fitting, which
in many domains entails significant cost of manual data labeling. An
alternative approach is application of data augmentation (DA) techniques that
aim at model regularization by creating additional observations from the
available ones. This survey focuses on two DA research streams: image mixing
and automated selection of augmentation strategies. First, the presented
methods are briefly described, and then qualitatively compared with respect to
their key characteristics. Various quantitative comparisons are also included
based on the results reported in recent DA literature. This review mainly
covers the methods published in the materials of top-tier conferences and in
leading journals in the years 2017-2021.
Related papers
- A Comprehensive Survey on Data Augmentation [55.355273602421384]
Data augmentation is a technique that generates high-quality artificial data by manipulating existing data samples.
Existing literature surveys only focus on a certain type of specific modality data.
We propose a more enlightening taxonomy that encompasses data augmentation techniques for different common data modalities.
arXiv Detail & Related papers (2024-05-15T11:58:08Z) - A Survey on Data Augmentation in Large Model Era [16.05117556207015]
Large models, encompassing large language and diffusion models, have shown exceptional promise in approximating human-level intelligence.
With continuous updates to these models, the existing reservoir of high-quality data may soon be depleted.
This paper offers an exhaustive review of large model-driven data augmentation methods.
arXiv Detail & Related papers (2024-01-27T14:19:33Z) - Semi-supervised Object Detection: A Survey on Recent Research and
Progress [2.2398477810999817]
Semi-supervised object detection (SSOD) has been paid more and more attentions due to its high research value and practicability.
We present a comprehensive and up-to-date survey on the SSOD approaches from five aspects.
arXiv Detail & Related papers (2023-06-25T02:54:03Z) - Domain Generalization for Mammographic Image Analysis with Contrastive
Learning [62.25104935889111]
The training of an efficacious deep learning model requires large data with diverse styles and qualities.
A novel contrastive learning is developed to equip the deep learning models with better style generalization capability.
The proposed method has been evaluated extensively and rigorously with mammograms from various vendor style domains and several public datasets.
arXiv Detail & Related papers (2023-04-20T11:40:21Z) - Label-Efficient Deep Learning in Medical Image Analysis: Challenges and
Future Directions [10.502964056448283]
Training models in medical imaging analysis typically require expensive and time-consuming collection of labeled data.
We extensively investigated over 300 recent papers to provide a comprehensive overview of progress on label-efficient learning strategies in MIA.
Specifically, we provide an in-depth investigation, covering not only canonical semi-supervised, self-supervised, and multi-instance learning schemes, but also recently emerged active and annotation-efficient learning strategies.
arXiv Detail & Related papers (2023-03-22T11:51:49Z) - Cross-Modal Fine-Tuning: Align then Refine [83.37294254884446]
ORCA is a cross-modal fine-tuning framework that extends the applicability of a single large-scale pretrained model to diverse modalities.
We show that ORCA obtains state-of-the-art results on 3 benchmarks containing over 60 datasets from 12 modalities.
arXiv Detail & Related papers (2023-02-11T16:32:28Z) - Research Trends and Applications of Data Augmentation Algorithms [77.34726150561087]
We identify the main areas of application of data augmentation algorithms, the types of algorithms used, significant research trends, their progression over time and research gaps in data augmentation literature.
We expect readers to understand the potential of data augmentation, as well as identify future research directions and open questions within data augmentation research.
arXiv Detail & Related papers (2022-07-18T11:38:32Z) - Guiding Generative Language Models for Data Augmentation in Few-Shot
Text Classification [59.698811329287174]
We leverage GPT-2 for generating artificial training instances in order to improve classification performance.
Our results show that fine-tuning GPT-2 in a handful of label instances leads to consistent classification improvements.
arXiv Detail & Related papers (2021-11-17T12:10:03Z) - Deep Visual Domain Adaptation [6.853165736531939]
Domain adaptation (DA) aims at improving the performance of a model on target domains by transferring the knowledge contained in different but related source domains.
With recent advances in deep learning models which are extremely data hungry, the interest for visual DA has significantly increased in the last decade.
arXiv Detail & Related papers (2020-12-28T10:40:09Z) - Generative Data Augmentation for Commonsense Reasoning [75.26876609249197]
G-DAUGC is a novel generative data augmentation method that aims to achieve more accurate and robust learning in the low-resource setting.
G-DAUGC consistently outperforms existing data augmentation methods based on back-translation.
Our analysis demonstrates that G-DAUGC produces a diverse set of fluent training examples, and that its selection and training approaches are important for performance.
arXiv Detail & Related papers (2020-04-24T06:12:10Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.