相关论文: U-GAT-IT: Unsupervised Generative Attentional Netw…

Unsupervised domain adaptation (UDA) for semantic segmentation is a promising task freeing people from heavy annotation work. However, domain discrepancies in low-level image statistics and high-level contexts compromise the segmentation…

Unsupervised image-to-image translation aims at learning a mapping between two visual domains. However, learning a translation across large geometry variations always ends up with failure. In this work, we present a novel…

Text-guided image manipulation tasks have recently gained attention in the vision-and-language community. While most of the prior studies focused on single-turn manipulation, our goal in this paper is to address the more challenging…

Over the last few years, the performance of inpainting to fill missing regions has shown significant improvements by using deep neural networks. Most of inpainting work create a visually plausible structure and texture, however, due to them…

Image translation with convolutional neural networks has recently been used as an approach to multimodal change detection. Existing approaches train the networks by exploiting supervised information of the change areas, which, however, is…

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution…

Unsupervised domain adaptation is critical in various computer vision tasks, such as object detection, instance segmentation, and semantic segmentation, which aims to alleviate performance degradation caused by domain-shift. Most of…

Existing unsupervised video-to-video translation methods fail to produce translated videos which are frame-wise realistic, semantic information preserving and video-level consistent. In this work, we propose UVIT, a novel unsupervised…

Self-training is an important class of unsupervised domain adaptation (UDA) approaches that are used to mitigate the problem of domain shift, when applying knowledge learned from a labeled source domain to unlabeled and heterogeneous target…

Unsupervised image-to-image translation aims to learn the mapping between two visual domains with unpaired samples. Existing works focus on disentangling domain-invariant content code and domain-specific style code individually for…

This paper develops a unified framework for image-to-image translation based on conditional diffusion models and evaluates this framework on four challenging image-to-image translation tasks, namely colorization, inpainting, uncropping, and…

While attention-based transformer networks achieve unparalleled success in nearly all language tasks, the large number of tokens (pixels) found in images coupled with the quadratic activation memory usage makes them prohibitive for problems…

Unsupervised domain adaptation (UDA) aims to transfer the knowledge learnt from a labeled source domain to an unlabeled target domain. Previous work is mainly built upon convolutional neural networks (CNNs) to learn domain-invariant…

Unsupervised domain adaptation enables to alleviate the need for pixel-wise annotation in the semantic segmentation. One of the most common strategies is to translate images from the source domain to the target domain and then align their…

Vehicle re-identification (reID) is to identify a target vehicle in different cameras with non-overlapping views. When deploy the well-trained model to a new dataset directly, there is a severe performance drop because of differences among…

Most models of visual attention aim at predicting either top-down or bottom-up control, as studied using different visual search and free-viewing tasks. In this paper we propose the Human Attention Transformer (HAT), a single model that…

Despite their generative power, diffusion models struggle to maintain style consistency across images conditioned on the same style prompt, hindering their practical deployment in creative workflows. While several training-free methods…

Deep learning models tend to underperform in the presence of domain shifts. Domain transfer has recently emerged as a promising approach wherein images exhibiting a domain shift are transformed into other domains for augmentation or…

We present a novel method, SALAD, for the challenging vision task of adapting a pre-trained "source" domain network to a "target" domain, with a small budget for annotation in the "target" domain and a shift in the label space. Further, the…

Shape assembly, which aims to reassemble separate parts into a complete object, has gained significant interest in recent years. Existing methods primarily rely on networks to predict the poses of individual parts, but often fail to…