Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling
- Convolutional neural networks encode images through a sequence of convolutions, normalizations and non-linearities as well as downsampling operations into potentially strong semantic embeddings. Yet, previous work showed that even slight mistakes during sampling, leading to aliasing, can be directly attributed to the networks' lack in robustness. To address such issues and facilitate simpler andConvolutional neural networks encode images through a sequence of convolutions, normalizations and non-linearities as well as downsampling operations into potentially strong semantic embeddings. Yet, previous work showed that even slight mistakes during sampling, leading to aliasing, can be directly attributed to the networks' lack in robustness. To address such issues and facilitate simpler and faster adversarial training, [12] recently proposed FLC pooling, a method for provably alias-free downsampling - in theory. In this work, we conduct a further analysis through the lens of signal processing and find that such current pooling methods, which address aliasing in the frequency domain, are still prone to spectral leakage artifacts. Hence, we propose aliasing and spectral artifact-free pooling, short ASAP. While only introducing a few modifications to FLC pooling, networks using ASAP as downsampling method exhibit higher native robustness against common corruptions, a property that FLC pooling was missing. ASAP also increases native robustness against adversarial attacks on high and low resolution data while maintaining similar clean accuracy or even outperforming the baseline.…
Document Type: | Article (unreviewed) |
---|---|
Zitierlink: | https://opus.hs-offenburg.de/8401 | Bibliografische Angaben |
Title (English): | Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling |
Author: | Julia GrabinskiStaff MemberORCiD, Janis KeuperStaff MemberORCiDGND, Margret Keuper |
Year of Publication: | 2023 |
Date of first Publication: | 2023/07/19 |
First Page: | 1 |
Last Page: | 10 |
DOI: | https://doi.org/10.48550/arXiv.2307.09804 |
Language: | English | Inhaltliche Informationen |
Institutes: | Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) |
Forschung / IMLA - Institute for Machine Learning and Analytics | |
Institutes: | Bibliografie | Formale Angaben |
Relevance: | Keine Relevanz |
Open Access: | Open Access |
Bronze | |
Licence (German): | Urheberrechtlich geschützt |
ArXiv Id: | http://arxiv.org/abs/2307.09804 |