Related papers: D3T-GAN: Data-Dependent Domain Transfer GANs for F…

We propose a novel method for solving regression tasks using few-shot or weak supervision. At the core of our method is the fundamental observation that GANs are incredibly successful at encoding semantic information within their latent…

Few shot learning aims to solve the data scarcity problem. If there is a domain shift between the test set and the training set, their performance will decrease a lot. This setting is called Cross-domain few-shot learning. However, this is…

Despite recent progress in Reinforcement Learning for robotics applications, many tasks remain prohibitively difficult to solve because of the expensive interaction cost. Transfer learning helps reduce the training time in the target domain…

Generative adversarial networks (GANs) have attained photo-realistic quality in image generation. However, how to best control the image content remains an open challenge. We introduce LatentKeypointGAN, a two-stage GAN which is trained…

Few-shot graph anomaly detection (GAD) has recently garnered increasing attention, which aims to discern anomalous patterns among abundant unlabeled test nodes under the guidance of a limited number of labeled training nodes. Existing…

Cross-view image translation is challenging because it involves images with drastically different views and severe deformation. In this paper, we propose a novel approach named Multi-Channel Attention SelectionGAN (SelectionGAN) that makes…

Denoising diffusion probabilistic models (DDPM) are powerful hierarchical latent variable models with remarkable sample generation quality and training stability. These properties can be attributed to parameter sharing in the generative…

Going beyond few-shot action recognition (FSAR), cross-domain FSAR (CDFSAR) has attracted recent research interests by solving the domain gap lying in source-to-target transfer learning. Existing CDFSAR methods mainly focus on joint…

Generative adversarial networks (GANs) are challenging to train stably, and a promising remedy of injecting instance noise into the discriminator input has not been very effective in practice. In this paper, we propose Diffusion-GAN, a…

Recently, few-shot object detection~(FSOD) has received much attention from the community, and many methods are proposed to address this problem from a knowledge transfer perspective. Though promising results have been achieved, these…

Text-to-image generation models have progressed considerably in recent years, which can now generate impressive realistic images from arbitrary text. Most of such models are trained on web-scale image-text paired datasets, which may not be…

In this study, we investigate the performance of few-shot classification models across different domains, specifically natural images and histopathological images. We first train several few-shot classification models on natural images and…

A central problem in unsupervised domain adaptation is determining what to transfer from labeled source domains to an unlabeled target domain. To handle high-dimensional observations (e.g., images), a line of approaches use deep learning to…

Domain shift between medical images from multicentres is still an open question for the community, which degrades the generalization performance of deep learning models. Generative adversarial network (GAN), which synthesize plausible…

Translating images from a source domain to a target domain for learning target models is one of the most common strategies in domain adaptive semantic segmentation (DASS). However, existing methods still struggle to preserve…

Learning to generate natural scenes has always been a daunting task in computer vision. This is even more laborious when generating images with very different views. When the views are very different, the view fields have little overlap or…

Interest in image-to-image translation has grown substantially in recent years with the success of unsupervised models based on the cycle-consistency assumption. The achievements of these models have been limited to a particular subset of…

Modern Generative Adversarial Networks are capable of creating artificial, photorealistic images from latent vectors living in a low-dimensional learned latent space. It has been shown that a wide range of images can be projected into this…

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…

Domain Adaptation is an actively researched problem in Computer Vision. In this work, we propose an approach that leverages unsupervised data to bring the source and target distributions closer in a learned joint feature space. We…