Emerging large-scale text-to-image generative models, e.g., Stable Diffu...
The generalization with respect to domain shifts, as they frequently app...
The generalization with respect to domain shifts, as they frequently app...
Joint synthesis of images and segmentation masks with generative adversa...
Training GANs in low-data regimes remains a challenge, as overfitting of...
Given a large number of training samples, GANs can achieve remarkable
pe...
Despite data augmentation being a de facto technique for boosting the
pe...
Among the major remaining challenges for generative adversarial networks...
Recently, there has been a growing interest in developing saliency metho...
Training of Generative Adversarial Networks (GANs) is notoriously fragil...
Multi-person pose estimation in images and videos is an important yet
ch...
Most state-of-the-art semi-supervised video object segmentation methods ...
Convolutional networks reach top quality in pixel-level object tracking ...
There have been remarkable improvements in the semantic labelling task i...
Inspired by recent advances of deep learning in instance segmentation an...
Semantic labelling and instance segmentation are two tasks that require
...