SuperpixelGridCut, SuperpixelGridMean and SuperpixelGridMix Data Augmentation
A novel approach of data augmentation based on irregular superpixel decomposition is proposed. This approach called SuperpixelGridMasks permits to extend original image datasets that are required by training stages of machine learning-related analysis architectures towards increasing their performances. Three variants named SuperpixelGridCut, SuperpixelGridMean and SuperpixelGridMix are presented. These grid-based methods produce a new style of image transformations using the dropping and fusing of information. Extensive experiments using various image classification models and datasets show that baseline performances can be significantly outperformed using our methods. The comparative study also shows that our methods can overpass the performances of other data augmentations. Experimental results obtained over image recognition datasets of varied natures show the efficiency of these new methods. SuperpixelGridCut, SuperpixelGridMean and SuperpixelGridMix codes are publicly available at https://github.com/hammoudiproject/SuperpixelGridMasks
Code (1)
Tasks
Data Augmentationimage-classificationImage ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Safe Augmentation: Learning Task-Specific Transformations from Data
Data augmentation is widely used as a part of the training process applied to deep learning models, especially in the computer vision domain. Currently, common data augmentation techniques are designed manually. Therefor…
Data AugmentationHandwritten image augmentation
In this paper, we introduce Handwritten augmentation, a new data augmentation for handwritten character images. This method focuses on augmenting handwritten image data by altering the shape of input characters in traini…
Data AugmentationImage AugmentationOptical Character RecognitionPositionImage, Text, and Speech Data Augmentation using Multimodal LLMs for Deep Learning: A Survey
In the past five years, research has shifted from traditional Machine Learning (ML) and Deep Learning (DL) approaches to leveraging Large Language Models (LLMs) , including multimodality, for data augmentation to enhance…
Data AugmentationImage AugmentationText AugmentationEvaluating the Effectiveness and Scalability of LLM-Based Data Augmentation for Retrieval
Compact dual-encoder models are widely used for retrieval owing to their efficiency and scalability. However, such models often underperform compared to their Large Language Model (LLM)-based retrieval counterparts, like…
Data AugmentationDeep AutoAugment
While recent automated data augmentation methods lead to state-of-the-art results, their design spaces and the derived data augmentation strategies still incorporate strong human priors. In this work, instead of fixing a…
AutoMLData AugmentationImage Classification