Deep learning has become the method of choice to tackle real-world problems in different
domains, partly because of its ability to learn from data and achieve impressive performance …

Recently, Optimal Transport has been proposed as a probabilistic framework in Machine
Learning for comparing and manipulating probability distributions. This is rooted in its rich …

Semantic segmentation has witnessed tremendous progress due to the proposal of various
advanced network architectures. However, they are extremely hungry for delicate …

AI Safety is a major concern in many deep learning applications such as autonomous
driving. Given a trained deep learning model, an important natural problem is how to reliably …

Not all semantics become confusing when deploying a semantic segmentation model for
real-world scene understanding of adverse weather. The true semantics of most pixels have …

Deep neural networks are usually data-starved, but manually annotation can be costly in
many specific tasks. For instance, the emotion recognition from the audio. However, there is …

Weakly supervised semantic segmentation (WSSS) aims to produce pixel-wise class
predictions with only image-level labels for training. To this end, previous methods adopt the …

Semantic segmentation of an incoming visual stream from cameras is an essential part of
the perception system of self-driving cars. State-of-the-art results in semantic segmentation …

We study the use of amortized optimization to predict optimal transport (OT) maps from the
input measures, which we call Meta OT. This helps repeatedly solve similar OT problems …

The unsupervised domain adaptation (UDA) has been widely adopted to alleviate the data
scalability issue, while the existing works usually focus on classifying independently discrete …