Related papers: Reusing Discriminators for Encoding: Towards Unsup…

Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available…

Person re-identification (re-ID) models trained on one domain often fail to generalize well to another. In our attempt, we present a "learning via translation" framework. In the baseline, we translate the labeled images from source to…

Image-to-image translation tasks have been widely investigated with Generative Adversarial Networks (GANs). However, existing approaches are mostly designed in an unsupervised manner while little attention has been paid to domain…

Neural machine translation aims at building a single large neural network that can be trained to maximize translation performance. The encoder-decoder architecture with an attention mechanism achieves a translation performance comparable to…

Thanks to their remarkable generative capabilities, GANs have gained great popularity, and are used abundantly in state-of-the-art methods and applications. In a GAN based model, a discriminator is trained to learn the real data…

Despite unconditional feature inversion being the foundation of many image synthesis applications, training an inverter demands a high computational budget, large decoding capacity and imposing conditions such as autoregressive priors. To…

Generative Adversarial Networks (GANs) have significantly advanced image synthesis through mapping randomly sampled latent codes to high-fidelity synthesized images. However, applying well-trained GANs to real image editing remains…

Recent studies have shown remarkable success in image-to-image translation for attribute transfer applications. However, most of existing approaches are based on deep learning and require an abundant amount of labeled data to produce good…

We consider the single image super-resolution problem in a more general case that the low-/high-resolution pairs and the down-sampling process are unavailable. Different from traditional super-resolution formulation, the low-resolution…

Image-to-image translation is to learn a mapping between images from a source domain and images from a target domain. In this paper, we introduce the attention mechanism directly to the generative adversarial network (GAN) architecture and…

Image Captioning (IC) has achieved astonishing developments by incorporating various techniques into the CNN-RNN encoder-decoder architecture. However, since CNN and RNN do not share the basic network component, such a heterogeneous…

Current unsupervised image-to-image translation techniques struggle to focus their attention on individual objects without altering the background or the way multiple objects interact within a scene. Motivated by the important role of…

Many applications can benefit from personalized image generation models, including image enhancement, video conferences, just to name a few. Existing works achieved personalization by fine-tuning one model for each person. While being…

Recently, several discriminative learning approaches have been proposed for effective image restoration, achieving convincing trade-off between image quality and computational efficiency. However, these methods require separate training for…

Generative adversarial network (GAN) has greatly improved the quality of unsupervised image generation. Previous GAN-based methods often require a large amount of high-quality training data while producing a small number (e.g., tens) of…

Image to image translation is the problem of transferring an image from a source domain to a different (but related) target domain. We present a new unsupervised image to image translation technique that leverages the underlying semantic…

In this paper, we design and train a Generative Image-to-text Transformer, GIT, to unify vision-language tasks such as image/video captioning and question answering. While generative models provide a consistent network architecture between…

The past year has witnessed a rapid development of masked image modeling (MIM). MIM is mostly built upon the vision transformers, which suggests that self-supervised visual representations can be done by masking input image parts while…

Intelligent vision is appealing in computer-assisted and robotic surgeries. Vision-based analysis with deep learning usually requires large labeled datasets, but manual data labeling is expensive and time-consuming in medical problems. We…

We present an alternative perspective on the training of generative adversarial networks (GANs), showing that the training step for a GAN generator decomposes into two implicit subproblems. In the first, the discriminator provides new…