Grid self-occlusion: a grid self-occlusion data augmentation for better classification

Deng, Xue; Zhao, Hua-An; Zhang, Hua; Zhang, Jing; Mei, Boping

doi:10.1007/s11760-022-02278-0

Cited by 2 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The lack of data leads to significant empirical risk in the model, and the imbalance between empirical risk and model complexity is one of the main reasons for overfitting in deep learning models. 21 High-quality annotated data require significant costs. Moreover, many application areas are unable to access big data.…”

Section: Data Augmentationmentioning

confidence: 99%

Self-transformation of encoded subregion image data augmentation for better classification

Huang,

Zhang,

Deng

2024

J. Electron. Imag.

Self Cite

View full text Add to dashboard Cite

Data augmentation has been proven to be an effective regularization strategy that can reduce over-fitting risks in deep learning models. Erasure based data augmentation is one of the most advanced solutions; however, random region erasure inevitably leads to excessive loss of object information and the introduction of a large amount of negative noise. In this work, a data augmentation method based on self-transformation of encoded image subregions is proposed. This method first designs an encoding mechanism based on random strategy to determine the object sub-regions of the transformation. Then, self-morphing strategies such as random cropping, rotation, and channel transformation are applied to the sub-regions to maintain the original feature information conditions and increase the local variance characteristics of the samples. Finally, we perform erasure on the non-discriminative triangular region generated after rotation of the object region. The proposed method is easy to implement, and a large number of experiments were conducted on challenging datasets. The algorithm achieved significant improvements in classification performance. On the CIFAR-100 dataset, the top-1 error rate decreased by 2.83%. For object detection, the average detection accuracy on the PASCAL VOC dataset increased from 79.83% to 82.15%, with the highest average accuracy improvement of 5.32% for a single category.

show abstract

Section: Data Augmentationmentioning

confidence: 99%