Related papers: CutMix: Regularization Strategy to Train Strong Cl…
Data augmentation is widely used to enhance generalization in visual classification tasks. However, traditional methods struggle when source and target domains differ, as in domain adaptation, due to their inability to address domain gaps.…
Deep convolutional neural networks have shown remarkable performance on various computer vision tasks, and yet, they are susceptible to picking up spurious correlations from the training signal. So called `shortcuts' can occur during…
Mix-based augmentation has been proven fundamental to the generalization of deep vision models. However, current augmentations only mix samples at the current data batch during training, which ignores the possible knowledge accumulated in…
In this paper, we introduce a novel data augmentation technique that combines the advantages of style augmentation and random erasing by selectively replacing image subregions with style-transferred patches. Our approach first applies a…
Images suffer from heavy spatial redundancy because pixels in neighboring regions are spatially correlated. Existing approaches strive to overcome this limitation by reducing less meaningful image regions. However, current leading methods…
As 3D point cloud analysis has received increasing attention, the insufficient scale of point cloud datasets and the weak generalization ability of networks become prominent. In this paper, we propose a simple and effective augmentation…
In this paper, we propose a novel data augmentation strategy named Cut-Thumbnail, that aims to improve the shape bias of the network. We reduce an image to a certain size and replace the random region of the original image with the reduced…
Modern deep networks can be better generalized when trained with noisy samples and regularization techniques. Mixup and CutMix have been proven to be effective for data augmentation to help avoid overfitting. Previous Mixup-based methods…
Neural networks are often over-parameterized and hence benefit from aggressive regularization. Conventional regularization methods, such as Dropout or weight decay, do not leverage the structures of the network's inputs and hidden states.…
The development of medical image segmentation using deep learning can significantly support doctors' diagnoses. Deep learning needs large amounts of data for training, which also requires data augmentation to extend diversity for preventing…
Dropout as a common regularizer to prevent overfitting in deep neural networks has been less effective in convolutional layers than in fully connected layers. This is because Dropout drops features randomly, without considering local…
Randomized smoothing (RS) has been shown to be a fast, scalable technique for certifying the robustness of deep neural network classifiers. However, methods based on RS require augmenting data with large amounts of noise, which leads to…
Overfitting is a well-known issue extending even to state-of-the-art (SOTA) Machine Learning (ML) models, resulting in reduced generalization, and a significant train-test performance gap. Mitigation measures include a combination of…
Mixed Sample Regularization (MSR), such as MixUp or CutMix, is a powerful data augmentation strategy to generalize convolutional neural networks. Previous empirical analysis has illustrated an orthogonal performance gain between MSR and…
The big breakthrough on the ImageNet challenge in 2012 was partially due to the `dropout' technique used to avoid overfitting. Here, we introduce a new approach called `Spectral Dropout' to improve the generalization ability of deep neural…
Few-shot learning aims to classify unseen classes with a few training examples. While recent works have shown that standard mini-batch training with a carefully designed training strategy can improve generalization ability for unseen…
This paper focuses on regularizing the training of the convolutional neural network (CNN). We propose a new regularization approach named ``PatchShuffle`` that can be adopted in any classification-oriented CNN models. It is easy to…
Data augmentation improves the generalization power of deep learning models by synthesizing more training samples. Sample-mixing is a popular data augmentation approach that creates additional data by combining existing samples. Recent…
Aligning machine representations with human understanding is key to improving interpretability of machine learning (ML) models. When classifying a new image, humans often explain their decisions by decomposing the image into concepts and…
Differences in staining and imaging procedures can cause significant color variations in histopathology images, leading to poor generalization when deploying deep-learning models trained from a different data source. Various color…