Related papers: Few Shot Generative Model Adaption via Relaxed Spa…

To mitigate the detection performance drop caused by domain shift, we aim to develop a novel few-shot adaptation approach that requires only a few target domain images with limited bounding box annotations. To this end, we first observe…

We address the problem of segmenting 3D multi-modal medical images in scenarios where very few labeled examples are available for training. Leveraging the recent success of adversarial learning for semi-supervised segmentation, we propose a…

In this paper, we explore the use of GAN-based few-shot data augmentation as a method to improve few-shot classification performance. We perform an exploration into how a GAN can be fine-tuned for such a task (one of which is in a…

The adaptation of a Generative Adversarial Network (GAN) aims to transfer a pre-trained GAN to a target domain with limited training data. In this paper, we focus on the one-shot case, which is more challenging and rarely explored in…

The effectiveness of generative adversarial approaches in producing images according to a specific style or visual domain has recently opened new directions to solve the unsupervised domain adaptation problem. It has been shown that source…

Modern GANs excel at generating high quality and diverse images. However, when transferring the pretrained GANs on small target data (e.g., 10-shot), the generator tends to replicate the training samples. Several methods have been proposed…

Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks. One appealing alternative is rendering synthetic data where ground-truth annotations are generated…

Conditional generative adversarial networks (cGANs) have demonstrated remarkable success due to their class-wise controllability and superior quality for complex generation tasks. Typical cGANs solve the joint distribution matching problem…

We propose a few-shot learning method for spatial regression. Although Gaussian processes (GPs) have been successfully used for spatial regression, they require many observations in the target task to achieve a high predictive performance.…

We propose a new approach to Generative Adversarial Networks (GANs) to achieve an improved performance with additional robustness to its so-called and well recognized mode collapse. We first proceed by mapping the desired data onto a…

Training a generative model with limited number of samples is a challenging task. Current methods primarily rely on few-shot model adaption to train the network. However, in scenarios where data is extremely limited (less than 10), the…

Deep learning has revolutionized various fields, yet its efficacy is hindered by overfitting and the requirement of extensive annotated data, particularly in few-shot learning scenarios where limited samples are available. This paper…

Domain Adaptation (DA) targets at adapting a model trained over the well-labeled source domain to the unlabeled target domain lying in different distributions. Existing DA normally assumes the well-labeled source domain is class-wise…

3D-aware image generation necessitates extensive training data to ensure stable training and mitigate the risk of overfitting. This paper first considers a novel task known as One-shot 3D Generative Domain Adaptation (GDA), aimed at…

Controlling the generative model to adapt a new domain with limited samples is a difficult challenge and it is receiving increasing attention. Recently, methods based on meta-learning have shown promising results for few-shot domain…

Training Generative Adversarial Networks (GAN) on high-fidelity images usually requires large-scale GPU-clusters and a vast number of training images. In this paper, we study the few-shot image synthesis task for GAN with minimum computing…

Due to the outstanding capability for data generation, Generative Adversarial Networks (GANs) have attracted considerable attention in unsupervised learning. However, training GANs is difficult, since the training distribution is dynamic…

Few-shot learning aims to recognize novel queries with limited support samples by learning from base knowledge. Recent progress in this setting assumes that the base knowledge and novel query samples are distributed in the same domains,…

Deep networks are prone to performance degradation when there is a domain shift between the source (training) data and target (test) data. Recent test-time adaptation methods update batch normalization layers of pre-trained source models…

Transferring the knowledge of pretrained networks to new domains by means of finetuning is a widely used practice for applications based on discriminative models. To the best of our knowledge this practice has not been studied within the…