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
翻译:提出了一个基于超像素不规则分解的数据增强新颖方法。 这个名为 SuperpixelGridMask 的方法允许扩展机器学习相关分析结构培训阶段所需的原始图像数据集, 以提高其性能。 介绍了三个变体, 名为 SuperpixelGridCut、 SuperpixelGridMean 和 SuperpixelGridMix 。 这些基于网格的方法产生一种新的图像转换风格, 使用投放和引信信息。 使用各种图像分类模型和数据集的广泛实验显示, 使用我们的方法可以大大超过基准性能。 比较研究还显示, 我们的方法可以超越其他数据增强的性能。 不同性质的图像识别数据集获得的实验结果显示了这些新方法的效率。 SuperpixelGridCut、 SuperpixelGridMian和SuperpixelGridMix代码可在https://github. com/hammoudificroject/ SuperplixGridMask 上公开查阅 http http:// https