Recent years have witnessed enormous progress in AI-related fields such as computer vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it …
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 …
We present a practical and robust deep learning solution for capturing and rendering novel views of complex real world scenes for virtual exploration. Previous approaches either …
Human pose is typically represented by a coordinate vector of body joints or their heatmap embeddings. While easy for data processing, unrealistic pose estimates are admitted due to …
Building home assistant robots has long been a goal for vision and robotics researchers. To achieve this task, a simulated environment with physically realistic simulation, sufficient …
You are holding in your hands… oh, come on, who holds books like this in their hands anymore? Anyway, you are reading this, and it means that I have managed to release one of …
In federated learning (FL), model performance typically suffers from client drift induced by data heterogeneity, and mainstream works focus on correcting client drift. We propose a …
In this paper, we study the problem of semi-supervised image recognition, which is to learn classifiers using both labeled and unlabeled images. We present Deep Co-Training, a deep …
Despite excellent performance on stationary test sets, deep neural networks (DNNs) can fail to generalize to out-of-distribution (OoD) inputs, including natural, non-adversarial ones …