Related papers: Semantically Robust Unpaired Image Translation for…

Semantic communications has received growing interest since it can remarkably reduce the amount of data to be transmitted without missing critical information. Most existing works explore the semantic encoding and transmission for text and…

To reduce network traffic and support environments with limited resources, a method for transmitting images with minimal transmission data is required. Several machine learning-based image compression methods, which compress the data size…

State-of-the-art text-to-image models produce visually impressive results but often struggle with precise alignment to text prompts, leading to missing critical elements or unintended blending of distinct concepts. We propose a novel…

Despite that the performance of image-to-image translation has been significantly improved by recent progress in generative models, current methods still suffer from severe degradation in training stability and sample quality when applied…

Recent studies show strong generative performance in domain translation especially by using transfer learning techniques on the unconditional generator. However, the control between different domain features using a single model is still…

We introduce a diffusion-based cross-domain image translator in the absence of paired training data. Unlike GAN-based methods, our approach integrates diffusion models to learn the image translation process, allowing for more coverable…

Recently image inpainting has witnessed rapid progress due to generative adversarial networks (GAN) that are able to synthesize realistic contents. However, most existing GAN-based methods for semantic inpainting apply an auto-encoder…

We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. Previous methods directly feed the semantic layout as input to the deep network, which is then…

Pretrained language models are long known to be subpar in capturing sentence and document-level semantics. Though heavily investigated, transferring perturbation-based methods from unsupervised visual representation learning to NLP remains…

Given the ever-increasing computational costs of modern machine learning models, we need to find new ways to reuse such expert models and thus tap into the resources that have been invested in their creation. Recent work suggests that the…

As a sequence-to-sequence generation task, neural machine translation (NMT) naturally contains intrinsic uncertainty, where a single sentence in one language has multiple valid counterparts in the other. However, the dominant methods for…

Visual data compression is shifting from human-centered reconstruction to machine-oriented representation coding. In this setting, an image is often mapped to a compact semantic embedding, which is then compressed and transmitted for…

A common goal of unpaired image-to-image translation is to preserve content consistency between source images and translated images while mimicking the style of the target domain. Due to biases between the datasets of both domains, many…

Recent studies on unsupervised image-to-image translation have made a remarkable progress by training a pair of generative adversarial networks with a cycle-consistent loss. However, such unsupervised methods may generate inferior results…

Unpaired image-to-image translation (I2I) is an ill-posed problem, as an infinite number of translation functions can map the source domain distribution to the target distribution. Therefore, much effort has been put into designing suitable…

Semantic communications, aiming at ensuring the successful delivery of the meaning of information, are expected to be one of the potential techniques for the next generation communications. However, the knowledge forming and synchronizing…

Unpaired Image-to-image Translation is a new rising and challenging vision problem that aims to learn a mapping between unaligned image pairs in diverse domains. Recent advances in this field like MUNIT and DRIT mainly focus on…

This work proposes a multi-image matching method to estimate semantic correspondences across multiple images. In contrast to the previous methods that optimize all pairwise correspondences, the proposed method identifies and matches only a…

Training deep generative models usually requires a large amount of data. To alleviate the data collection cost, the task of zero-shot GAN adaptation aims to reuse well-trained generators to synthesize images of an unseen target domain…

Unsupervised on-the-fly back-translation, in conjunction with multilingual pretraining, is the dominant method for unsupervised neural machine translation. Theoretically, however, the method should not work in general. We therefore conduct…