8 citations · 18 across the 12 of their papers we have counts for
6 papers · 1 filter
Adversarial Wear and Tear: Exploiting Natural Damage for Generating Physical-World Adversarial Examples
Samra Irshad, Seungkyu Lee, Nassir Navab +2
The presence of adversarial examples in the physical world poses significant challenges to the deployment of Deep Neural Networks in safety-critical applications such as autonomous…
SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge
Hao Ding, Yuqian Zhang, Tuxun Lu +39
Surgical data science has seen rapid advancement with the excellent performance of end-to-end deep neural networks (DNNs). Despite their successes, DNNs have been proven susceptibl…
LINe: Out-of-Distribution Detection by Leveraging Important Neurons
Yong Hyun Ahn, Gyeong-Moon Park, Seong Tae Kim
It is important to quantify the uncertainty of input samples, especially in mission-critical domains such as autonomous driving and healthcare, where failure predictions on out-of-…
Exploiting Diversity of Unlabeled Data for Label-Efficient Semi-Supervised Active Learning
Felix Buchert, Nassir Navab, Seong Tae Kim
The availability of large labeled datasets is the key component for the success of deep learning. However, annotating labels on large datasets is generally time-consuming and expen…
Neural Response Interpretation through the Lens of Critical Pathways
Ashkan Khakzar, Soroosh Baselizadeh, Saurabh Khanduja +3
Is critical input information encoded in specific sparse pathways within the neural network? In this work, we discuss the problem of identifying these critical pathways and subsequ…
GLOWin: A Flow-based Invertible Generative Framework for Learning Disentangled Feature Representations in Medical Images
Aadhithya Sankar, Matthias Keicher, Rami Eisawy +4
Disentangled representations can be useful in many downstream tasks, help to make deep learning models more interpretable, and allow for control over features of synthetically gene…