5 papers
Enhancing Classifier Conservativeness and Robustness by Polynomiality
Ziqi Wang, Marco Loog
We illustrate the detrimental effect, such as overconfident decisions, that exponential behavior can have in methods like classical LDA and logistic regression. We then show how po…
Respecting Domain Relations: Hypothesis Invariance for Domain Generalization
Ziqi Wang, Marco Loog, Jan van Gemert
In domain generalization, multiple labeled non-independent and non-identically distributed source domains are available during training while neither the data nor the labels of tar…
Black Magic in Deep Learning: How Human Skill Impacts Network Training
Kanav Anand, Ziqi Wang, Marco Loog +1
How does a user's prior experience with deep learning impact accuracy? We present an initial study based on 31 participants with different levels of experience. Their task is to pe…
Attention-Aware Age-Agnostic Visual Place Recognition
Ziqi Wang, Jiahui Li, Seyran Khademi +1
A cross-domain visual place recognition (VPR) task is proposed in this work, i.e., matching images of the same architectures depicted in different domains. VPR is commonly treated…
How to Manipulate CNNs to Make Them Lie: the GradCAM Case
Tom Viering, Ziqi Wang, Marco Loog +1
Recently many methods have been introduced to explain CNN decisions. However, it has been shown that some methods can be sensitive to manipulation of the input. We continue this li…