Using mixup as regularization and tuning hyper-parameters for ResNets
This work provides an incremental improvement for computer vision practitioners using ResNets with limited data.
The authors revisited ResNet50 and improved its performance on image classification by using mixup data-augmentation as regularization and tuning hyper-parameters, achieving competitive results on standard benchmarks.
While novel computer vision architectures are gaining traction, the impact of model architectures is often related to changes or exploring in training methods. Identity mapping-based architectures ResNets and DenseNets have promised path-breaking results in the image classification task and are go-to methods for even now if the data given is fairly limited. Considering the ease of training with limited resources this work revisits the ResNets and improves the ResNet50 \cite{resnets} by using mixup data-augmentation as regularization and tuning the hyper-parameters.