2000 character limit reached
FFT-based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images (2403.14335v1)
Published 21 Mar 2024 in cs.CV
Abstract: Improving model robustness in case of corrupted images is among the key challenges to enable robust vision systems on smart devices, such as robotic agents. Particularly, robust test-time performance is imperative for most of the applications. This paper presents a novel approach to improve robustness of any classification model, especially on severely corrupted images. Our method (FROST) employs high-frequency features to detect input image corruption type, and select layer-wise feature normalization statistics. FROST provides the state-of-the-art results for different models and datasets, outperforming competitors on ImageNet-C by up to 37.1% relative gain, improving baseline of 40.9% mCE on severe corruptions.
- “Benchmarking neural network robustness to common corruptions and perturbations,” ICLR, 2019.
- “Hybridaugment++: Unified frequency spectra perturbations for model robustness,” in ICCV, 2023.
- “TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation,” in ICLR, 2023.
- “Amplitude-phase recombination: Rethinking robustness of convolutional neural networks in frequency domain,” in ICCV, 2021.
- “Frequency domain model augmentation for adversarial attack,” in ECCV, 2022.
- “Imagenet large scale visual recognition challenge,” IJCV, 2015.
- “Learning multiple layers of features from tiny images,” 2009.
- “Improving robustness of feature representations to image deformations using powered convolution in cnns,” in CVPR, 2017.
- “Augmax: Adversarial composition of random augmentations for robust training,” in NeurIPS, 2021.
- “Autoaugment: Learning augmentation strategies from data,” in CVPR, 2019.
- “Pixmix: Dreamlike pictures comprehensively improve safety measures,” CVPR, 2021.
- “AugMix: A simple data processing method to improve robustness and uncertainty,” ICLR, 2020.
- “Are transformers more robust than cnns?,” in NeurIPS, 2021.
- “Improving robustness against common corruptions by covariate shift adaptation,” NeurIPS, 2020.
- “Sita: Single image test-time adaptation,” ArXiv, 2021.
- “Improving robustness against common corruptions with frequency biased models,” in ICCV, 2021.
- “A spectral view of randomized smoothing under common corruptions: Benchmarking and improving certified robustness,” in ECCV, 2022.
- “Improving robustness without sacrificing accuracy with patch gaussian augmentation,” ArXiv, 2019.
- Richard Zhang, “Making convolutional networks shift-invariant again,” in ICML, 2019.
- “A simple way to make neural networks robust against diverse image corruptions,” in ECCV, 2020.
- “The many faces of robustness: A critical analysis of out-of-distribution generalization,” in ICCV, 2021.
- “An algorithm for the machine calculation of complex fourier series,” MCOM, 1965.
- “Comparing partitions,” Journal of Classification, 1985.
- “Multi-scale fast fourier transform based attention network for remote-sensing image super-resolution,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023.
- “On performance of multiscale sparse fast fourier transform algorithm,” Circuits, Systems and Signal Processing, 2020.
- “Deep residual learning for image recognition,” in CVPR, 2016.
- “An image is worth 16x16 words: Transformers for image recognition at scale,” ICLR, 2021.
- Elena Camuffo (7 papers)
- Umberto Michieli (40 papers)
- Jijoong Moon (9 papers)
- Daehyun Kim (16 papers)
- Mete Ozay (65 papers)