Learning Continuous Rotation Canonicalization with Radial Beam Sampling

• URL: http://arxiv.org/abs/2206.10690v1
• Date: Tue, 21 Jun 2022 19:12:06 GMT
• Title: Learning Continuous Rotation Canonicalization with Radial Beam Sampling
• Authors: Johann Schmidt and Sebastian Stober
• Abstract summary: We present a radial beam-based image canonicalization model, short BIC. Our model allows for maximal continuous angle regression and canonicalizes arbitrary center-rotated input images. As a pre-processing model, this enables rotation-invariant vision pipelines with model-agnostic rotation-sensitive downstream predictions.
• Score: 2.8935588665357077
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Nearly all state of the art vision models are sensitive to image rotations. Existing methods often compensate for missing inductive biases by using augmented training data to learn pseudo-invariances. Alongside the resource demanding data inflation process, predictions often poorly generalize. The inductive biases inherent to convolutional neural networks allow for translation equivariance through kernels acting parallely to the horizontal and vertical axes of the pixel grid. This inductive bias, however, does not allow for rotation equivariance. We propose a radial beam sampling strategy along with radial kernels operating on these beams to inherently incorporate center-rotation covariance. Together with an angle distance loss, we present a radial beam-based image canonicalization model, short BIC. Our model allows for maximal continuous angle regression and canonicalizes arbitrary center-rotated input images. As a pre-processing model, this enables rotation-invariant vision pipelines with model-agnostic rotation-sensitive downstream predictions. We show that our end-to-end trained angle regressor is able to predict continuous rotation angles on several vision datasets, i.e. FashionMNIST, CIFAR10, COIL100, and LFW.

Related papers

• Are the Latent Representations of Foundation Models for Pathology Invariant to Rotation? [3.407509559779547]
  Self-supervised foundation models for digital pathology encode small patches from H&E whole slide images into latent representations used for downstream tasks. This study investigates the rotational invariance of latent representations across twelve foundation models by quantifying the alignment between non-rotated and rotated patches using mutual $k$-nearest neighbours and cosine distance.
  arXiv  Detail & Related papers  (2024-12-16T16:23:05Z)
• von Mises Quasi-Processes for Bayesian Circular Regression [57.88921637944379]
  We explore a family of expressive and interpretable distributions over circle-valued random functions. The resulting probability model has connections with continuous spin models in statistical physics. For posterior inference, we introduce a new Stratonovich-like augmentation that lends itself to fast Markov Chain Monte Carlo sampling.
  arXiv  Detail & Related papers  (2024-06-19T01:57:21Z)
• FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection [28.47314201641291]
  We introduce a Fully Rotation-Equivariant Oriented Object Detector (FRED) Our proposed method delivers comparable performance on DOTA-v1.0 and outperforms by 1.5 mAP on DOTA-v1.5, all while significantly reducing the model parameters to 16%.
  arXiv  Detail & Related papers  (2023-12-22T09:31:43Z)
• DiffusionPCR: Diffusion Models for Robust Multi-Step Point Cloud Registration [73.37538551605712]
  Point Cloud Registration (PCR) estimates the relative rigid transformation between two point clouds. We propose formulating PCR as a denoising diffusion probabilistic process, mapping noisy transformations to the ground truth. Our experiments showcase the effectiveness of our DiffusionPCR, yielding state-of-the-art registration recall rates (95.3%/81.6%) on 3D and 3DLoMatch.
  arXiv  Detail & Related papers  (2023-12-05T18:59:41Z)
• A Variational Perspective on Solving Inverse Problems with Diffusion Models [101.831766524264]
  Inverse tasks can be formulated as inferring a posterior distribution over data. This is however challenging in diffusion models since the nonlinear and iterative nature of the diffusion process renders the posterior intractable. We propose a variational approach that by design seeks to approximate the true posterior distribution.
  arXiv  Detail & Related papers  (2023-05-07T23:00:47Z)
• Towards Flexible Inductive Bias via Progressive Reparameterization Scheduling [25.76814731638375]
  There are two de facto standard architectures in computer vision: Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) We show these approaches overlook that the optimal inductive bias also changes according to the target data scale changes. The more convolution-like inductive bias is included in the model, the smaller the data scale is required where the ViT-like model outperforms the ResNet performance.
  arXiv  Detail & Related papers  (2022-10-04T04:20:20Z)
• SPIN: Simplifying Polar Invariance for Neural networks Application to vision-based irradiance forecasting [2.624902795082451]
  Unwrapping an image into its polar coordinates provides a more explicit representation to train a convolutional architecture. We show that this preprocessing step significantly improves prediction results by standardising the scene representation. This transformation magnifies the area surrounding the centre of the rotation, leading to more accurate short-term irradiance predictions.
  arXiv  Detail & Related papers  (2021-11-29T12:58:57Z)
• Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence [100.6913091147422]
  Existing rotated object detectors are mostly inherited from the horizontal detection paradigm. In this paper, we are motivated to change the design of rotation regression loss from induction paradigm to deduction methodology.
  arXiv  Detail & Related papers  (2021-06-03T14:29:19Z)
• Extreme Rotation Estimation using Dense Correlation Volumes [73.35119461422153]
  We present a technique for estimating the relative 3D rotation of an RGB image pair in an extreme setting. We observe that, even when images do not overlap, there may be rich hidden cues as to their geometric relationship. We propose a network design that can automatically learn such implicit cues by comparing all pairs of points between the two input images.
  arXiv  Detail & Related papers  (2021-04-28T02:00:04Z)
• Rotated Ring, Radial and Depth Wise Separable Radial Convolutions [13.481518628796692]
  In this work, we address trainable rotation invariant convolutions and the construction of nets. On the one hand, we show that our approach is rotationally invariant for different models and on different public data sets. The rotationally adaptive convolution models presented are more computationally intensive than normal convolution models.
  arXiv  Detail & Related papers  (2020-10-02T09:01:51Z)
• Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data [52.78581260260455]
  We propose a general method to construct a convolutional layer that is equivariant to transformations from any specified Lie group. We apply the same model architecture to images, ball-and-stick molecular data, and Hamiltonian dynamical systems.
  arXiv  Detail & Related papers  (2020-02-25T17:40:38Z)

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.