Related papers: Conditional Adversarial Networks for Multi-Domain …

Generative Adversarial Networks (GANs) have achieved great success in generating realistic images. Most of these are conditional models, although acquisition of class labels is expensive and time-consuming in practice. To reduce the…

Ideally, what confuses neural network should be confusing to humans. However, recent experiments have shown that small, imperceptible perturbations can change the network prediction. To address this gap in perception, we propose a novel…

Generative Adversarial Nets (GANs) have shown promise in image generation and semi-supervised learning (SSL). However, existing GANs in SSL have two problems: (1) the generator and the discriminator (i.e. the classifier) may not be optimal…

We study how to generate captions that are not only accurate in describing an image but also discriminative across different images. The problem is both fundamental and interesting, as most machine-generated captions, despite phenomenal…

Generating multiple categories of texts is a challenging task and draws more and more attention. Since generative adversarial nets (GANs) have shown competitive results on general text generation, they are extended for category text…

We propose discriminative adversarial networks (DAN) for semi-supervised learning and loss function learning. Our DAN approach builds upon generative adversarial networks (GANs) and conditional GANs but includes the key differentiator of…

Most existing unsupervised domain adaptation methods mainly focused on aligning the marginal distributions of samples between the source and target domains. This setting does not sufficiently consider the class distribution information…

The GANs are generative models whose random samples realistically reflect natural images. It also can generate samples with specific attributes by concatenating a condition vector into the input, yet research on this field is not well…

We propose a method for semi-supervised semantic segmentation using an adversarial network. While most existing discriminators are trained to classify input images as real or fake on the image level, we design a discriminator in a fully…

Generative adversarial networks (GANs) have great successes on synthesizing data. However, the existing GANs restrict the discriminator to be a binary classifier, and thus limit their learning capacity for tasks that need to synthesize…

Domain generalization approaches aim to learn a domain invariant prediction model for unknown target domains from multiple training source domains with different distributions. Significant efforts have recently been committed to broad…

Generative adversarial networks (GANs)successfully generate high quality data by learning amapping from a latent vector to the data. Various studies assert that the latent space of a GAN is semanticallymeaningful and can be utilized for…

Inspired by the success of adversarial learning, we propose a new end-to-end unsupervised deep learning framework for monocular depth estimation consisting of two Generative Adversarial Networks (GAN), deeply coupled with a structured…

Generative Adversarial Networks (GANs) produce systematically better quality samples when class label information is provided., i.e. in the conditional GAN setup. This is still observed for the recently proposed Wasserstein GAN formulation…

Despite the substantial progress in recent years, the image captioning techniques are still far from being perfect.Sentences produced by existing methods, e.g. those based on RNNs, are often overly rigid and lacking in variability. This…

This work proposes the continuous conditional generative adversarial network (CcGAN), the first generative model for image generation conditional on continuous, scalar conditions (termed regression labels). Existing conditional GANs (cGANs)…

Recent studies have found that deep learning systems are vulnerable to adversarial examples; e.g., visually unrecognizable adversarial images can easily be crafted to result in misclassification. The robustness of neural networks has been…

Sufficient supervised information is crucial for any machine learning models to boost performance. However, labeling data is expensive and sometimes difficult to obtain. Active learning is an approach to acquire annotations for data from a…

We present a novel variant of Domain Adversarial Networks with impactful improvements to the loss functions, training paradigm, and hyperparameter optimization. New loss functions are defined for both forks of the DANN network, the label…

Convolutional neural network (CNN) have proven its success for semantic segmentation, which is a core task of emerging industrial applications such as autonomous driving. However, most progress in semantic segmentation of urban scenes is…