Avoiding overfitting: A survey on regularization methods for convolutional neural networks
CFGD Santos, JP Papa - ACM Computing Surveys (CSUR), 2022 - dl.acm.org
Several image processing tasks, such as image classification and object detection, have
been significantly improved using Convolutional Neural Networks (CNN). Like ResNet and …
been significantly improved using Convolutional Neural Networks (CNN). Like ResNet and …
A survey of mix-based data augmentation: Taxonomy, methods, applications, and explainability
Data augmentation (DA) is indispensable in modern machine learning and deep neural
networks. The basic idea of DA is to construct new training data to improve the model's …
networks. The basic idea of DA is to construct new training data to improve the model's …
MedViT: a robust vision transformer for generalized medical image classification
Abstract Convolutional Neural Networks (CNNs) have advanced existing medical systems
for automatic disease diagnosis. However, there are still concerns about the reliability of …
for automatic disease diagnosis. However, there are still concerns about the reliability of …
How does mixup help with robustness and generalization?
Mixup is a popular data augmentation technique based on taking convex combinations of
pairs of examples and their labels. This simple technique has been shown to substantially …
pairs of examples and their labels. This simple technique has been shown to substantially …
Uncertainty baselines: Benchmarks for uncertainty & robustness in deep learning
High-quality estimates of uncertainty and robustness are crucial for numerous real-world
applications, especially for deep learning which underlies many deployed ML systems. The …
applications, especially for deep learning which underlies many deployed ML systems. The …
Fmix: Enhancing mixed sample data augmentation
E Harris, A Marcu, M Painter, M Niranjan… - arXiv preprint arXiv …, 2020 - arxiv.org
Mixed Sample Data Augmentation (MSDA) has received increasing attention in recent
years, with many successful variants such as MixUp and CutMix. By studying the mutual …
years, with many successful variants such as MixUp and CutMix. By studying the mutual …
A unified analysis of mixed sample data augmentation: A loss function perspective
We propose the first unified theoretical analysis of mixed sample data augmentation
(MSDA), such as Mixup and CutMix. Our theoretical results show that regardless of the …
(MSDA), such as Mixup and CutMix. Our theoretical results show that regardless of the …
Mixmo: Mixing multiple inputs for multiple outputs via deep subnetworks
Recent strategies achieved ensembling"" for free"" by fitting concurrently diverse
subnetworks inside a single base network. The main idea during training is that each …
subnetworks inside a single base network. The main idea during training is that each …
Survey: Image mixing and deleting for data augmentation
Neural networks are prone to overfitting and memorizing data patterns. To avoid over-fitting
and enhance their generalization and performance, various methods have been suggested …
and enhance their generalization and performance, various methods have been suggested …
The benefits of mixup for feature learning
Mixup, a simple data augmentation method that randomly mixes two data points via linear
interpolation, has been extensively applied in various deep learning applications to gain …
interpolation, has been extensively applied in various deep learning applications to gain …