paper-with-me

홈 › Papers

SuperpixelGridCut, SuperpixelGridMean and SuperpixelGridMix Data Augmentation

2022-04-11 · Karim Hammoudi, Adnane Cabani, Bouthaina Slika, Halim Benhabiles, Fadi Dornaika, Mahmoud Melkemi

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

📄 PDF Abstract BibTeX arXiv:2204.08458

Code (1)

hammoudiproject/superpixelgridmasks 공식 구현

Tasks

Data Augmentationimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

SuperpixelGridMasks Karim Hammoudi, Adnane Cabani, Bouthaina Slika, Halim Benhabiles, Fadi Dornaika and Mahmoud Melkemi. SuperpixelGridCut, SuperpixelGridMean and SuperpixelGridMix Data Augmentation,…

Similar Papers 제목 키워드 기반

Safe Augmentation: Learning Task-Specific Transformations from Data

2019-07-30 · Irynei Baran, Orest Kupyn, Arseny Kravchenko

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 Augmentation

Handwritten image augmentation

2023-08-26 · Mahendran N

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 RecognitionPosition

Image, Text, and Speech Data Augmentation using Multimodal LLMs for Deep Learning: A Survey

2025-01-29 · Ranjan Sapkota, Shaina Raza, Maged Shoman, Achyut Paudel 외

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 Augmentation

Evaluating the Effectiveness and Scalability of LLM-Based Data Augmentation for Retrieval

2025-09-19 · Pranjal A. Chitale, Bishal Santra, Yashoteja Prabhu, Amit Sharma arxiv

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 Augmentation

Deep AutoAugment

2022-03-11 · Yu Zheng, Zhi Zhang, Shen Yan, Mi Zhang

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