Data Augmentation

Data augmentation for deep visual recognition using superpixel based pairwise image fusion
Data augmentation is an important paradigm for boosting the generalization capability of deep learning in image classification tasks. …
Cite Code Project Project DOI URL
LCAMix: Local-and-contour aware grid mixing based data augmentation for medical image segmentation
Medical image segmentation often faces challenges related to overfitting, primarily due to the limited and complex training samples. …
Cite Code Project Project DOI URL
LGCOAMix: Local and Global Context-and-Object-Part-Aware Superpixel-Based Data Augmentation for Deep Visual Recognition
Cutmix-based data augmentation, which uses a cut-and-paste strategy, has shown remarkable generalization capabilities in deep learning. …
Cite Code Project DOI
Object-centric Contour-aware Data Augmentation Using Superpixels of Varying Granularity
Regional dropout strategies have demonstrated to be very effective in improving both the performance and the generalization capability …
Cite DOI URL