相关论文: Generatively Augmented Neural Network Watchdog for…

A neural network deployed in the wild may be asked to make predictions for inputs that were drawn from a different distribution than that of the training data. A plethora of work has demonstrated that it is easy to find or synthesize inputs…

Fine-grained image recognition is central to many multimedia tasks such as search, retrieval and captioning. Unfortunately, these tasks are still challenging since the appearance of samples of the same class can be more different than those…

We study out-of-distribution (OOD) prediction behavior of neural networks when they classify images from unseen classes or corrupted images. To probe the OOD behavior, we introduce a new measure, nearest category generalization (NCG), where…

This paper presents a methodology for image classification using Graph Neural Network (GNN) models. We transform the input images into region adjacency graphs (RAGs), in which regions are superpixels and edges connect neighboring…

A Triangle Generative Adversarial Network ($\Delta$-GAN) is developed for semi-supervised cross-domain joint distribution matching, where the training data consists of samples from each domain, and supervision of domain correspondence is…

Current developments in computer vision and deep learning allow to automatically generate hyper-realistic images, hardly distinguishable from real ones. In particular, human face generation achieved a stunning level of realism, opening new…

We present variational generative adversarial networks, a general learning framework that combines a variational auto-encoder with a generative adversarial network, for synthesizing images in fine-grained categories, such as faces of a…

The accelerating advancement of generative models has introduced new challenges for detecting AI-generated images, especially in real-world scenarios where novel generation techniques emerge rapidly. Existing learning paradigms are likely…

Various Graph Neural Networks (GNNs) have been successful in analyzing data in non-Euclidean spaces, however, they have limitations such as oversmoothing, i.e., information becomes excessively averaged as the number of hidden layers…

Deep neural networks can be effective means to automatically classify aerial images but is easy to overfit to the training data. It is critical for trained neural networks to be robust to variations that exist between training and test…

We present the self-encoder, a neural network trained to guess the identity of each data sample. Despite its simplicity, it learns a very useful representation of data, in a self-supervised way. Specifically, the self-encoder learns to…

Generative Adversarial Networks (GANs) typically learn a distribution of images in a large image dataset, and are then able to generate new images from this distribution. However, each natural image has its own internal statistics, captured…

Modern convolutional neural networks (CNNs) are able to achieve human-level object classification accuracy on specific tasks, and currently outperform competing models in explaining complex human visual representations. However, the…

Data augmentation is often used to enlarge datasets with synthetic samples generated in accordance with the underlying data distribution. To enable a wider range of augmentations, we explore negative data augmentation strategies (NDA)that…

In this study, we propose a three-stage training approach of neural networks for both photometric redshift estimation of galaxies and detection of out-of-distribution (OOD) objects. Our approach comprises supervised and unsupervised…

One of the biggest issues facing the use of machine learning in medical imaging is the lack of availability of large, labelled datasets. The annotation of medical images is not only expensive and time consuming but also highly dependent on…

Unsupervised learning of anomaly detection in high-dimensional data, such as images, is a challenging problem recently subject to intense research. Through careful modelling of the data distribution of normal samples, it is possible to…

While neural networks can be trained to map from one specific dataset to another, they usually do not learn a generalized transformation that can extrapolate accurately outside the space of training. For instance, a generative adversarial…

Generative adversarial networks (GANs) have demonstrated to be successful at generating realistic real-world images. In this paper we compare various GAN techniques, both supervised and unsupervised. The effects on training stability of…

Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes…