Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of
uncertainties during both optimization and decision making processes. They have been …

Quantifying the uncertainty of supervised learning models plays an important role in making
more reliable predictions. Epistemic uncertainty, which usually is due to insufficient …

Low-level details and high-level semantics are both essential to the semantic segmentation
task. However, to speed up the model inference, current approaches almost always sacrifice …

Spotting objects that are visually adapted to their surroundings is challenging for both
humans and AI. Conventional generic/salient object detection techniques are suboptimal for …

Nowadays, there are outstanding strides towards a future with autonomous vehicles on our
roads. While the perception of autonomous vehicles performs well under closed-set …

Full-image dependencies provide useful contextual information to benefit visual
understanding problems. In this work, we propose a Criss-Cross Network (CCNet) for …

Semantic segmentation requires large amounts of pixel-wise annotations to learn accurate
models. In this paper, we present a video prediction-based methodology to scale up training …

Video segmentation—partitioning video frames into multiple segments or objects—plays a
critical role in a broad range of practical applications, from enhancing visual effects in movie …

Self-supervised paradigms for monocular depth estimation are very appealing since they do
not require ground truth annotations at all. Despite the astonishing results yielded by such …

For robots to navigate and interact more richly with the world around them, they will likely
require a deeper understanding of the world in which they operate. In robotics and related …