What Does CNN Shift Invariance Look Like? A Visualization Study

• URL: http://arxiv.org/abs/2011.04127v1
• Date: Mon, 9 Nov 2020 01:16:30 GMT
• Title: What Does CNN Shift Invariance Look Like? A Visualization Study
• Authors: Jake Lee, Junfeng Yang, Zhangyang Wang
• Abstract summary: Feature extraction with convolutional neural networks (CNNs) is a popular method to represent images for machine learning tasks. We focus on measuring and visualizing the shift invariance of extracted features from popular off-the-shelf CNN models. We conclude that features extracted from popular networks are not globally invariant, and that biases and artifacts exist within this variance.
• Score: 87.79405274610681
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Feature extraction with convolutional neural networks (CNNs) is a popular method to represent images for machine learning tasks. These representations seek to capture global image content, and ideally should be independent of geometric transformations. We focus on measuring and visualizing the shift invariance of extracted features from popular off-the-shelf CNN models. We present the results of three experiments comparing representations of millions of images with exhaustively shifted objects, examining both local invariance (within a few pixels) and global invariance (across the image frame). We conclude that features extracted from popular networks are not globally invariant, and that biases and artifacts exist within this variance. Additionally, we determine that anti-aliased models significantly improve local invariance but do not impact global invariance. Finally, we provide a code repository for experiment reproduction, as well as a website to interact with our results at https://jakehlee.github.io/visualize-invariance.

Related papers

• Truly Scale-Equivariant Deep Nets with Fourier Layers [14.072558848402362]
  In computer vision, models must be able to adapt to changes in image resolution to effectively carry out tasks such as image segmentation. Recent works have made progress in developing scale-equivariant convolutional neural networks, through weight-sharing and kernel resizing. We propose a novel architecture based on Fourier layers to achieve truly scale-equivariant deep nets.
  arXiv  Detail & Related papers  (2023-11-06T07:32:27Z)
• Revisiting Data Augmentation for Rotational Invariance in Convolutional Neural Networks [0.29127054707887967]
  We investigate how best to include rotational invariance in a CNN for image classification. Our experiments show that networks trained with data augmentation alone can classify rotated images nearly as well as in the normal unrotated case.
  arXiv  Detail & Related papers  (2023-10-12T15:53:24Z)
• The Change You Want to See (Now in 3D) [65.61789642291636]
  The goal of this paper is to detect what has changed, if anything, between two "in the wild" images of the same 3D scene. We contribute a change detection model that is trained entirely on synthetic data and is class-agnostic. We release a new evaluation dataset consisting of real-world image pairs with human-annotated differences.
  arXiv  Detail & Related papers  (2023-08-21T01:59:45Z)
• Causal Transportability for Visual Recognition [70.13627281087325]
  We show that standard classifiers fail because the association between images and labels is not transportable across settings. We then show that the causal effect, which severs all sources of confounding, remains invariant across domains. This motivates us to develop an algorithm to estimate the causal effect for image classification.
  arXiv  Detail & Related papers  (2022-04-26T15:02:11Z)
• Do Deep Networks Transfer Invariances Across Classes? [123.84237389985236]
  We show how a generative approach for learning the nuisance transformations can help transfer invariances across classes. Our results provide one explanation for why classifiers generalize poorly on unbalanced and longtailed distributions.
  arXiv  Detail & Related papers  (2022-03-18T04:38:18Z)
• Quantised Transforming Auto-Encoders: Achieving Equivariance to Arbitrary Transformations in Deep Networks [23.673155102696338]
  Convolutional Neural Networks (CNNs) are equivariant to image translation. We propose an auto-encoder architecture whose embedding obeys an arbitrary set of equivariance relations simultaneously. We demonstrate results of successful re-rendering of transformed versions of input images on several datasets.
  arXiv  Detail & Related papers  (2021-11-25T02:26:38Z)
• Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training [0.76146285961466]
  This paper assesses whether standard CNNs can support human-like online invariance by training models to recognize images of synthetic 3D objects that undergo several transformations. We show that standard supervised CNNs trained on transformed objects can acquire strong invariances on novel classes even when trained with as few as 50 objects taken from 10 classes.
  arXiv  Detail & Related papers  (2021-10-04T14:29:43Z)
• Shift Invariance Can Reduce Adversarial Robustness [20.199887291186364]
  Shift invariance is a critical property of CNNs that improves performance on classification. We show that invariance to circular shifts can also lead to greater sensitivity to adversarial attacks.
  arXiv  Detail & Related papers  (2021-03-03T21:27:56Z)
• 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 into Inter-Image Invariance for Unsupervised Visual Representations [108.33534231219464]
  We present a study to better understand the role of inter-image invariance learning. Online labels converge faster than offline labels. Semi-hard negative samples are more reliable and unbiased than hard negative samples.
  arXiv  Detail & Related papers  (2020-08-26T17:44:23Z)

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.