Related papers: TokenMix: Rethinking Image Mixing for Data Augment…
Semi-supervised semantic segmentation has witnessed remarkable advancements in recent years. However, existing algorithms are based on convolutional neural networks and directly applying them to Vision Transformers poses certain limitations…
CutMix is a vital augmentation strategy that determines the performance and generalization ability of vision transformers (ViTs). However, the inconsistency between the mixed images and the corresponding labels harms its efficacy. Existing…
Convolutional neural networks (CNN) are capable of learning robust representation with different regularization methods and activations as convolutional layers are spatially correlated. Based on this property, a large variety of regional…
CutMix is a data augmentation strategy that cuts and pastes image patches to mixup training data. Existing methods pick either random or salient areas which are often inconsistent to labels, thus misguiding the training model. By our…
Mixup is a commonly adopted data augmentation technique for image classification. Recent advances in mixup methods primarily focus on mixing based on saliency. However, many saliency detectors require intense computation and are especially…
In this study, we propose a novel data augmentation method that introduces the concept of CutMix into the generation process of diffusion models, thereby exploiting both the ability of diffusion models to generate natural and…
Data mixing strategies (e.g., CutMix) have shown the ability to greatly improve the performance of convolutional neural networks (CNNs). They mix two images as inputs for training and assign them with a mixed label with the same ratio.…
Although certain vision transformer (ViT) and CNN architectures generalize well on vision tasks, it is often impractical to use them on green, edge, or desktop computing due to their computational requirements for training and even testing.…
Data augmentation is a powerful technique to increase the diversity of data, which can effectively improve the generalization ability of neural networks in image recognition tasks. Recent data mixing based augmentation strategies have…
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…
Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers. They have proved to be effective for guiding the model to attend on less discriminative parts of objects (e.g. leg as…
Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed…
Semantic segmentation using convolutional neural networks (CNN) is a crucial component in image analysis. Training a CNN to perform semantic segmentation requires a large amount of labeled data, where the production of such labeled data is…
Mixup-based augmentation has been found to be effective for generalizing models during training, especially for Vision Transformers (ViTs) since they can easily overfit. However, previous mixup-based methods have an underlying prior…
While deep neural networks have achieved remarkable performance, data augmentation has emerged as a crucial strategy to mitigate overfitting and enhance network performance. These techniques hold particular significance in industrial…
Recent studies have integrated convolutions into transformers to introduce inductive bias and improve generalization performance. However, the static nature of conventional convolution prevents it from dynamically adapting to input…
Cutmix-based data augmentation, which uses a cut-and-paste strategy, has shown remarkable generalization capabilities in deep learning. However, existing methods primarily consider global semantics with image-level constraints, which…
We propose a novel neural architecture for computer vision -- WaveMix -- that is resource-efficient and yet generalizable and scalable. While using fewer trainable parameters, GPU RAM, and computations, WaveMix networks achieve comparable…
In this paper, we propose a method using the fusion of CNN and transformer structure to improve image classification performance. In the case of CNN, information about a local area on an image can be extracted well, but there is a limit to…
Detection Transformer (DETR) is a Transformer architecture based object detection model. In this paper, we demonstrate that it can also be used as a data augmenter. We term our approach as DETR assisted CutMix, or DeMix for short. DeMix…