FrequencyLowCut Pooling – Plug & Play against Catastrophic Overfitting
- Over the last years, Convolutional Neural Networks (CNNs) have been the dominating neural architecture in a wide range of computer vision tasks. From an image and signal processing point of view, this success might be a bit surprising as the inherent spatial pyramid design of most CNNs is apparently violating basic signal processing laws, i.e. Sampling Theorem in their down-sampling operations.Over the last years, Convolutional Neural Networks (CNNs) have been the dominating neural architecture in a wide range of computer vision tasks. From an image and signal processing point of view, this success might be a bit surprising as the inherent spatial pyramid design of most CNNs is apparently violating basic signal processing laws, i.e. Sampling Theorem in their down-sampling operations. However, since poor sampling appeared not to affect model accuracy, this issue has been broadly neglected until model robustness started to receive more attention. Recent work in the context of adversarial attacks and distribution shifts, showed after all, that there is a strong correlation between the vulnerability of CNNs and aliasing artifacts induced by poor down-sampling operations. This paper builds on these findings and introduces an aliasing free down-sampling operation which can easily be plugged into any CNN architecture: FrequencyLowCut pooling. Our experiments show, that in combination with simple and Fast Gradient Sign Method (FGSM) adversarial training, our hyper-parameter free operator substantially improves model robustness and avoids catastrophic overfitting. Our code is available at https://github.com/GeJulia/flc_pooling…
Document Type: | Conference Proceeding |
---|---|
Conference Type: | Konferenzartikel |
Zitierlink: | https://opus.hs-offenburg.de/6442 | Bibliografische Angaben |
Title (English): | FrequencyLowCut Pooling – Plug & Play against Catastrophic Overfitting |
Conference: | European Conference on Computer Vision (ECCV), October 23-27, 2022, Tel Aviv |
Author: | Julia GrabinskiStaff MemberORCiD, Steffen Jung, Janis KeuperStaff MemberORCiDGND, Margret Keuper |
Year of Publication: | 2022 |
First Page: | 1 |
Last Page: | 23 |
Parent Title (English): | ECCV 2022 Papers |
URL: | https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136740036.pdf |
URL: | https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136740036-supp.pdf |
Language: | English | Inhaltliche Informationen |
Institutes: | Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) |
Forschung / IMLA - Institute for Machine Learning and Analytics | |
Institutes: | Bibliografie |
Tag: | Robustness | Formale Angaben |
Relevance: | Konferenzbeitrag: h5-Index > 30 |
Open Access: | Open Access |
Bronze | |
Licence (German): | Urheberrechtlich geschützt |