Machine learning heavily relies on data, but real-world applications often encounter various
data-related issues. These include data of poor quality, insufficient data points leading to …

Generative adversarial networks (GANs) have recently become a hot research topic;
however, they have been studied since 2014, and a large number of algorithms have been …

Deep generative models are becoming increasingly powerful, now generating diverse high
fidelity photo-realistic samples given text prompts. Have they reached the point where …

Recent image generation models such as Stable Diffusion have exhibited an impressive
ability to generate fairly realistic images starting from a simple text prompt. Could such …

Unsupervised domain adaptation aims to align a labeled source domain and an unlabeled
target domain, but it requires to access the source data which often raises concerns in data …

We demonstrate that it is possible to perform face-related computer vision in the wild using
synthetic data alone. The community has long enjoyed the benefits of synthesizing training …

Self-training is a competitive approach in domain adaptive segmentation, which trains the
network with the pseudo labels on the target domain. However inevitably, the pseudo labels …

Level 5 autonomy for self-driving cars requires a robust visual perception system that can
parse input images under any visual condition. However, existing semantic segmentation …

We describe a simple method for unsupervised domain adaptation, whereby the
discrepancy between the source and target distributions is reduced by swapping the low …

Deep models trained on source domain lack generalization when evaluated on unseen
target domains with different data distributions. The problem becomes even more …