Search Results for author:
Found 11 papers, 2 papers with code
Frozen Feature Augmentation for Few-Shot Image Classification
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.
Detecting Adversarial Perturbations in Multi-Task Perception
In this paper, we (i) propose a novel adversarial perturbation detection scheme based on multi-task perception of complex vision tasks (i. e., depth estimation and semantic segmentation).
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
Our paper addresses both machine learning experts and safety engineers: The former ones might profit from the broad range of machine learning topics covered and discussions on limitations of recent methods.
Improving Online Performance Prediction for Semantic Segmentation
In this work we address the task of observing the performance of a semantic segmentation deep neural network (DNN) during online operation, i. e., during inference, which is of high importance in safety-critical applications such as autonomous driving.
The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing
Although CNNs obtain state-of-the-art performance on clean images, almost imperceptible changes to the input, referred to as adversarial perturbations, may lead to fatal deception.
From a Fourier-Domain Perspective on Adversarial Examples to a Wiener Filter Defense for Semantic Segmentation
Despite recent advancements, deep neural networks are not robust against adversarial perturbations.
Transferable Universal Adversarial Perturbations Using Generative Models
Using our generated non-targeted UAPs, we obtain an average fooling rate of 93. 36% on the source models (state of the art: 82. 16%).
Class-Incremental Learning for Semantic Segmentation Re-Using Neither Old Data Nor Old Labels
While neural networks trained for semantic segmentation are essential for perception in autonomous driving, most current algorithms assume a fixed number of classes, presenting a major limitation when developing new autonomous driving systems with the need of additional classes.
Improved Noise and Attack Robustness for Semantic Segmentation by Using Multi-Task Training with Self-Supervised Depth Estimation
We show the effectiveness of our method on the Cityscapes dataset, where our multi-task training approach consistently outperforms the single-task semantic segmentation baseline in terms of both robustness vs. noise and in terms of adversarial attacks, without the need for depth labels in training.
Towards Corner Case Detection for Autonomous Driving
The progress in autonomous driving is also due to the increased availability of vast amounts of training data for the underlying machine learning approaches.
GAN- vs. JPEG2000 Image Compression for Distributed Automotive Perception: Higher Peak SNR Does Not Mean Better Semantic Segmentation
The high amount of sensors required for autonomous driving poses enormous challenges on the capacity of automotive bus systems.
