The goal of semantic segmentation is to segment the input image according to semantic
information and predict the semantic category of each pixel from a given label set. With the …

The past few years have witnessed the significant impacts of wearable electronics/photonics
on various aspects of our daily life, for example, healthcare monitoring and treatment …

Abstract Out-of-distribution (OOD) detection is vital to safety-critical machine learning
applications and has thus been extensively studied, with a plethora of methods developed in …

Prevalent semantic segmentation solutions, despite their different network designs (FCN
based or attention based) and mask decoding strategies (parametric softmax based or pixel …

Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of machine
learning systems. For instance, in autonomous driving, we would like the driving system to …

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined
object categories. This restricted form of supervision limits their generality and usability since …

For machine learning systems to be reliable, we must understand their performance in
unseen, out-of-distribution environments. In this paper, we empirically show that out-of …

Determining whether inputs are out-of-distribution (OOD) is an essential building block for
safely deploying machine learning models in the open world. However, previous methods …

For future learning systems, incremental learning is desirable because it allows for: efficient
resource usage by eliminating the need to retrain from scratch at the arrival of new data; …

Inspired by progress in unsupervised representation learning for natural language, we
examine whether similar models can learn useful representations for images. We train a …