Recent advances in deep learning have led to the development of accurate and efficient
models for various computer vision applications such as classification, segmentation, and …

Anomaly segmentation is a critical task for driving applications, and it is approached
traditionally as a per-pixel classification problem. However, reasoning individually about …

Abstract The performance of Multi-Source Unsupervised Domain Adaptation depends
significantly on the effectiveness of transfer from labeled source domain samples. In this …

Under the domain shift, cross-domain few-shot object detection aims to adapt object
detectors in the target domain with a few annotated target data. There exists two significant …

Obtaining manual labels is time-consuming and labor-intensive on cardiac image
sequences. Few-shot segmentation can utilize limited labels to learn new tasks. However, it …

The focus of this work is sign spotting--given a video of an isolated sign, our task is to identify
whether and where it has been signed in a continuous, co-articulated sign language video …

In this paper we consider the task of semantic segmentation in autonomous driving
applications. Specifically, we consider the cross-domain few-shot setting where training can …

In few-shot domain adaptation (FDA), classifiers for the target domain are trained with\emph
{accessible} labeled data in the source domain (SD) and few labeled data in the target …

The focus of this work is sign spotting–given a video of an isolated sign, our task is to identify
whether and where it has been signed in a continuous, co-articulated sign language video …

Segmenting unknown or anomalous object instances is a critical task in autonomous driving
applications, and it is approached traditionally as a per-pixel classification problem …