CutMix is a data augmentation technique that addresses the issue of information loss and inefficiency present in regional dropout strategies. Instead of removing pixels and filling them with black or grey pixels or Gaussian noise, you replace the removed regions with a patch from another image, while the ground truth labels are mixed proportionally to the number of pixels of combined images.
CutMix was proposed in CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features (Yun et al., 2019)
Model Accuracy of 81%
The technique is quite systematically named - we are literally mixing up the features and their corresponding labels. Implementation-wise it's simple. Neural networks are prone to memorizing corrupt labels. mixup relaxes this by combining different features with one another (same happens for the labels too) so that a network does not get overconfident about the relationship between the features and their labels.
Mixup is specifically useful when we are not sure about selecting a set of augmentation transforms for a given dataset, medical imaging datasets, for example. mixup can be extended to a variety of data modalities such as computer vision, natural language processing, speech, and so on.
mixup is a domain-agnostic data augmentation technique proposed in mixup: Beyond Empirical Risk Minimization by Zhang et al.
Model Accuracy of 89%
AugMix, a data processing technique that mixes augmented images and enforces consistent embeddings of the augmented images, which results in increased robustness and improved uncertainty calibration. AugMix does not require tuning to work correctly, as with random cropping or CutOut, and thus enables plug-and-play data augmentation. AugMix significantly improves robustness and uncertainty measures on challenging image classification benchmarks, closing the gap between previous methods and the best possible performance by more than half in some cases. With AugMix, we obtain state-of-the-art on ImageNet-C, ImageNet-P and in uncertainty estimation when the train and test distribution do not match
AugMix technique proposed: A Simple Data Processing Method to Improve Robustness and Uncertainty by Hendrycks, Dan and Mu, Norman and Cubuk, Ekin D. and Zoph, Barret and Gilmer, Justin and Lakshminarayanan, Balaji.
Model Accuracy of __%
Fill up this form to request access.
Public API User Documentation.
Try it out, Go ahead and upload an image.