Pascal Mettes

Less than Few: Self-Shot Video Instance Segmentation

2022 · arXiv (Cornell University)

The goal of this paper is to bypass the need for labelled examples in few-shot video understanding at run time. While proven effective, in many practical video settings even labelling a few examples appears unrealistic. …

Infinite Class Mixup

2023 · UvA-DARE (University of Amsterdam)

Mixup is a widely adopted strategy for training deep networks, where additional samples are augmented by interpolating inputs and labels of training pairs. Mixup has shown to improve classification performance, network calibration, and out-of-distribution generalisation. …