← Search

Andreas Bär

2 accepted papers

2024

Frozen Feature Augmentation for Few-Shot Image Classification

CVPR 2024poster

Training a linear classifier or lightweight model on top of pretrained vision model outputs so-called 'frozen features' leads to impressive performance on a number of downstream few-shot tasks. Currently frozen features are not modified during training. On the other hand when networks are trained di…

Cited by 9SourcePDFScholar
2022

Detecting Adversarial Perturbations in Multi-Task Perception

IROS 2022poster

While deep neural networks (DNNs) achieve impressive performance on environment perception tasks, their sensitivity to adversarial perturbations limits their use in practical applications. In this paper, we (i) propose a novel adversarial perturbation detection scheme based on multi-task perception…

Cited by 23SourcecodeScholar