How to augment your ViTs? Consistency loss and StyleAug, a random style transfer augmentation
원문 초록
The Vision Transformer (ViT) architecture has recently achieved competitive performance across a variety of computer vision tasks. One of the motivations behind ViTs is weaker inductive biases, when compared to convolutional neural networks (CNNs). However this also makes ViTs more difficult to train. They require very large training datasets, heavy regularization, and strong data augmentations. The data augmentation strategies used to train ViTs have largely been inherited from CNN training, despite the significant differences between the two architectures. In this work, we empirical evaluated how different data augmentation strategies performed on CNN (e.g., ResNet) versus ViT architectures for image classification. We introduced a style transfer data augmentation, termed StyleAug, which worked best for training ViTs, while RandAugment and Augmix typically worked best for training CNNs. We also found that, in addition to a classification loss, using a consistency loss between multiple augmentations of the same image was especially helpful when training ViTs.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Transferring Styles for Reduced Texture Bias and Improved Robustness in Semantic Segmentation Networks
DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation
Robust Training with Data Augmentation for Medical Imaging Classification
Compositional Attribute Imbalance in Vision Datasets
IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature Representation
DGSSC: A Deep Generative Spectral-Spatial Classifier for Imbalanced Hyperspectral Imagery
토론
이 논문과 연결된 포럼 글이 아직 없습니다.