openmixup and Awesome-Mixup
The toolbox for visual representation learning and the survey of mixup augmentations are complements, as the former provides an implementation framework for various mixup techniques while the latter offers a comprehensive overview and analysis of those techniques and their extensions.
About openmixup
Westlake-AI/openmixup
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
Combines mixup data augmentation techniques with supervised, semi-supervised, and self-supervised learning pipelines using a modular OpenMMLab-compatible architecture. Supports both CNN and Transformer backbones across contrastive and masked image modeling pre-training methods, integrating downstream evaluation with Detectron2 and MMSegmentation for detection and segmentation tasks.
About Awesome-Mixup
Westlake-AI/Awesome-Mixup
[Survey] Awesome List of Mixup Augmentation and Beyond (https://arxiv.org/abs/2409.05202)
Scores updated daily from GitHub, PyPI, and npm data. How scores work