Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Function

• URL: http://arxiv.org/abs/2110.00899v1
• Date: Sun, 3 Oct 2021 01:00:52 GMT
• Title: Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Function
• Authors: Md Tahmid Hossain, Shyh Wei Teng, Ferdous Sohel, Guojun Lu
• Abstract summary: Deep convolutional networks are vulnerable to image translation or shift. The textbook solution is low-pass filtering before down-sampling. We show that Depth Adaptive Blurring is more effective, as opposed to monotonic blurring.
• Score: 7.888131635057012
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep convolutional networks are vulnerable to image translation or shift, partly due to common down-sampling layers, e.g., max-pooling and strided convolution. These operations violate the Nyquist sampling rate and cause aliasing. The textbook solution is low-pass filtering (blurring) before down-sampling, which can benefit deep networks as well. Even so, non-linearity units, such as ReLU, often re-introduce the problem, suggesting that blurring alone may not suffice. In this work, first, we analyse deep features with Fourier transform and show that Depth Adaptive Blurring is more effective, as opposed to monotonic blurring. To this end, we outline how this can replace existing down-sampling methods. Second, we introduce a novel activation function -- with a built-in low pass filter, to keep the problem from reappearing. From experiments, we observe generalisation on other forms of transformations and corruptions as well, e.g., rotation, scale, and noise. We evaluate our method under three challenging settings: (1) a variety of image translations; (2) adversarial attacks -- both $\ell_{p}$ bounded and unbounded; and (3) data corruptions and perturbations. In each setting, our method achieves state-of-the-art results and improves clean accuracy on various benchmark datasets.

Related papers

• Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains [19.573629029170128]
  This paper presents an innovative framework designed to train an image deblurring algorithm tailored to a specific camera device. It works by transforming a blurry input image, which is challenging to deblur, into another blurry image that is more amenable to deblurring.
  arXiv  Detail & Related papers  (2024-03-24T15:58:48Z)
• Neural Fields with Thermal Activations for Arbitrary-Scale Super-Resolution [56.089473862929886]
  We present a novel way to design neural fields such that points can be queried with an adaptive Gaussian PSF. With its theoretically guaranteed anti-aliasing, our method sets a new state of the art for arbitrary-scale single image super-resolution.
  arXiv  Detail & Related papers  (2023-11-29T14:01:28Z)
• Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling [11.72025865314187]
  Convolutional neural networks encode images through a sequence of convolutions, normalizations and non-linearities as well as downsampling operations. Previous work showed that even slight mistakes during sampling, leading to aliasing, can be directly attributed to the networks' lack in robustness. We propose aliasing and spectral artifact-free pooling, short ASAP.
  arXiv  Detail & Related papers  (2023-07-19T07:47:23Z)
• Deep Dynamic Scene Deblurring from Optical Flow [53.625999196063574]
  Deblurring can provide visually more pleasant pictures and make photography more convenient. It is difficult to model the non-uniform blur mathematically. We develop a convolutional neural network (CNN) to restore the sharp images from the deblurred features.
  arXiv  Detail & Related papers  (2023-01-18T06:37:21Z)
• Tuning-free Plug-and-Play Hyperspectral Image Deconvolution with Deep Priors [6.0622962428871885]
  We introduce a tuning-free Plug-and-Play (Play) algorithm for HSI deconvolution. Specifically, we use the alternating direction multipliers (ADMM) to decompose the problem into two iterative sub-problems. A flexible blind 3D denoising network (B3DDN) is designed to learn deep priors and to solve the denoising sub-problem with different noise levels.
  arXiv  Detail & Related papers  (2022-11-28T13:41:14Z)
• N2V2 -- Fixing Noise2Void Checkerboard Artifacts with Modified Sampling Strategies and a Tweaked Network Architecture [66.03918859810022]
  We present two modifications to the vanilla N2V setup that both help to reduce the unwanted artifacts considerably. We validate our modifications on a range of microscopy and natural image data.
  arXiv  Detail & Related papers  (2022-11-15T21:12:09Z)
• Contrastive Learning for Joint Normal Estimation and Point Cloud Filtering [12.602645108896636]
  We propose a novel deep learning method to jointly estimate normals and filter point clouds. We first introduce a 3D patch based contrastive learning framework, with noise corruption as an augmentation. Experimental results show that our method well supports the two tasks simultaneously and preserves sharp features and fine details.
  arXiv  Detail & Related papers  (2022-08-14T09:16:25Z)
• Transferable Sparse Adversarial Attack [62.134905824604104]
  We introduce a generator architecture to alleviate the overfitting issue and thus efficiently craft transferable sparse adversarial examples. Our method achieves superior inference speed, 700$times$ faster than other optimization-based methods.
  arXiv  Detail & Related papers  (2021-05-31T06:44:58Z)
• Permuted AdaIN: Reducing the Bias Towards Global Statistics in Image Classification [97.81205777897043]
  Recent work has shown that convolutional neural network classifiers overly rely on texture at the expense of shape cues. We make a similar but different distinction between shape and local image cues, on the one hand, and global image statistics, on the other. Our method, called Permuted Adaptive Instance Normalization (pAdaIN), reduces the representation of global statistics in the hidden layers of image classifiers.
  arXiv  Detail & Related papers  (2020-10-09T16:38:38Z)
• Delving Deeper into Anti-aliasing in ConvNets [42.82751522973616]
  Aliasing refers to the phenomenon that high frequency signals degenerate into completely different ones after sampling. We propose an adaptive content-aware low-pass filtering layer, which predicts separate filter weights for each spatial location and channel group.
  arXiv  Detail & Related papers  (2020-08-21T17:56:04Z)
• The Power of Triply Complementary Priors for Image Compressive Sensing [89.14144796591685]
  We propose a joint low-rank deep (LRD) image model, which contains a pair of complementaryly trip priors. We then propose a novel hybrid plug-and-play framework based on the LRD model for image CS. To make the optimization tractable, a simple yet effective algorithm is proposed to solve the proposed H-based image CS problem.
  arXiv  Detail & Related papers  (2020-05-16T08:17:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.