相关论文: Understanding the Benefits of Image Augmentations

Convolutional Neural Networks (CNNs) serve as the workhorse of deep learning, finding applications in various fields that rely on images. Given sufficient data, they exhibit the capacity to learn a wide range of concepts across diverse…

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…

In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping,…

Data augmentation is a popular technique largely used to enhance the training of convolutional neural networks. Although many of its benefits are well known by deep learning researchers and practitioners, its implicit regularization…

In recent years, hypercomplex-inspired neural networks (HCNNs) have been used to improve deep learning architectures due to their ability to enable channel-based weight sharing, treat colors as a single entity, and improve representational…

Data augmentations are important ingredients in the recipe for training robust neural networks, especially in computer vision. A fundamental question is whether neural network features encode data augmentation transformations. To answer…

CNNs have made an undeniable impact on computer vision through the ability to learn high-capacity models with large annotated training sets. One of their remarkable properties is the ability to transfer knowledge from a large source dataset…

Recent results suggest that reinitializing a subset of the parameters of a neural network during training can improve generalization, particularly for small training sets. We study the impact of different reinitialization methods in several…

Image classification has been a popular task due to its feasibility in real-world applications. Training neural networks by feeding them RGB images has demonstrated success over it. Nevertheless, improving the classification accuracy and…

Owing to flexible architectures of deep convolutional neural networks (CNNs), CNNs are successfully used for image denoising. However, they suffer from the following drawbacks: (i) deep network architecture is very difficult to train. (ii)…

Convolutional Neural Networks (CNN) offer state of the art performance in various computer vision tasks. Many of those tasks require different subtypes of affine invariances (scale, rotational, translational) to image transformations.…

Neural saturation in Deep Neural Networks (DNNs) has been studied extensively, but remains relatively unexplored in Convolutional Neural Networks (CNNs). Understanding and alleviating the effects of convolutional kernel saturation is…

Faithfully reconstructing 3D geometry and generating novel views of scenes are critical tasks in 3D computer vision. Despite the widespread use of image augmentations across computer vision applications, their potential remains…

Image augmentation techniques apply transformation functions such as rotation, shearing, or color distortion on an input image. These augmentations were proven useful in improving neural networks' generalization ability. In this paper, we…

Several image processing tasks, such as image classification and object detection, have been significantly improved using Convolutional Neural Networks (CNN). Like ResNet and EfficientNet, many architectures have achieved outstanding…

Residual networks (ResNets) represent a powerful type of convolutional neural network (CNN) architecture, widely adopted and used in various tasks. In this work we propose an improved version of ResNets. Our proposed improvements address…

We measure the influence of image augmentations and training dataset size when training a deep neural network to classify galaxy morphology. Data augmentation is an integral step when training machine learning models and often astronomers…

Recent studies revealed that convolutional neural networks do not generalize well to small image transformations, e.g. rotations by a few degrees or translations of a few pixels. To improve the robustness to such transformations, we propose…

Convolutional Neural Networks (CNNs) have advanced significantly in visual representation learning and recognition. However, they face notable challenges in performance and computational efficiency when dealing with real-world, multi-scale…

For all the ways convolutional neural nets have revolutionized computer vision in recent years, one important aspect has received surprisingly little attention: the effect of image size on the accuracy of tasks being trained for. Typically,…