On the Hidden Waves of Image
- URL: http://arxiv.org/abs/2310.12976v1
- Date: Thu, 19 Oct 2023 17:59:37 GMT
- Title: On the Hidden Waves of Image
- Authors: Yinpeng Chen and Dongdong Chen and Xiyang Dai and Mengchen Liu and Lu
Yuan and Zicheng Liu and Youzuo Lin
- Abstract summary: We introduce an intriguing phenomenon-the successful reconstruction of images using a set of one-way wave equations with hidden and learnable speeds.
Each individual image corresponds to a solution with a unique initial condition, which can be computed from the original image using a visual encoder.
- Score: 104.05734286732941
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this paper, we introduce an intriguing phenomenon-the successful
reconstruction of images using a set of one-way wave equations with hidden and
learnable speeds. Each individual image corresponds to a solution with a unique
initial condition, which can be computed from the original image using a visual
encoder (e.g., a convolutional neural network). Furthermore, the solution for
each image exhibits two noteworthy mathematical properties: (a) it can be
decomposed into a collection of special solutions of the same one-way wave
equations that are first-order autoregressive, with shared coefficient matrices
for autoregression, and (b) the product of these coefficient matrices forms a
diagonal matrix with the speeds of the wave equations as its diagonal elements.
We term this phenomenon hidden waves, as it reveals that, although the speeds
of the set of wave equations and autoregressive coefficient matrices are
latent, they are both learnable and shared across images. This represents a
mathematical invariance across images, providing a new mathematical perspective
to understand images.
Related papers
- Computational ghost imaging with hybrid transforms by integrating Hadamard, discrete cosine, and Haar matrices [4.542999605715059]
The image information can be conveniently reconstructed by the corresponding inverse matrices.
For an object of staggered stripes, only one bucket signal survives in the Hadamard-cosine, Haar-Hadamard, and Haar-cosine hybridization sets.
arXiv Detail & Related papers (2024-05-06T09:40:33Z) - Quantum optical classifier with superexponential speedup [3.262230127283452]
We present a quantum optical pattern recognition method for binary classification tasks.
It classifies an object in terms of the rate of two-photon coincidences at the output of a Hong-Ou-Mandel interferometer.
arXiv Detail & Related papers (2024-04-23T17:55:49Z) - On Sinkhorn's Algorithm and Choice Modeling [6.43826005042477]
We show that the associated maximum likelihood estimation problems are equivalent to a classic matrix balancing problem with target row and column sums.
This perspective opens doors between two seemingly unrelated research areas.
We draw inspirations from these connections and resolve important open problems on the study of Sinkhorn's algorithm.
arXiv Detail & Related papers (2023-09-30T05:20:23Z) - Image as First-Order Norm+Linear Autoregression: Unveiling Mathematical
Invariance [104.05734286732941]
FINOLA represents each image in the latent space as a first-order autoregressive process.
We demonstrate the ability of FINOLA to auto-regress up to a 256x256 feature map.
We also leverage FINOLA for self-supervised learning by employing a simple masked prediction approach.
arXiv Detail & Related papers (2023-05-25T17:59:50Z) - A quantum algorithm for the linear Vlasov equation with collisions [0.0]
We present a quantum algorithm that simulates the linearized Vlasov equation with and without collisions.
We show that a quadratic speedup in system size is attainable.
arXiv Detail & Related papers (2023-03-06T19:19:30Z) - Third quantization of open quantum systems: new dissipative symmetries
and connections to phase-space and Keldysh field theory formulations [77.34726150561087]
We reformulate the technique of third quantization in a way that explicitly connects all three methods.
We first show that our formulation reveals a fundamental dissipative symmetry present in all quadratic bosonic or fermionic Lindbladians.
For bosons, we then show that the Wigner function and the characteristic function can be thought of as ''wavefunctions'' of the density matrix.
arXiv Detail & Related papers (2023-02-27T18:56:40Z) - Quantum algorithms for matrix operations and linear systems of equations [65.62256987706128]
We propose quantum algorithms for matrix operations using the "Sender-Receiver" model.
These quantum protocols can be used as subroutines in other quantum schemes.
arXiv Detail & Related papers (2022-02-10T08:12:20Z) - Joint Estimation of Image Representations and their Lie Invariants [57.3768308075675]
Images encode both the state of the world and its content.
The automatic extraction of this information is challenging because of the high-dimensionality and entangled encoding inherent to the image representation.
This article introduces two theoretical approaches aimed at the resolution of these challenges.
arXiv Detail & Related papers (2020-12-05T00:07:41Z) - Eigendecomposition-Free Training of Deep Networks for Linear
Least-Square Problems [107.3868459697569]
We introduce an eigendecomposition-free approach to training a deep network.
We show that our approach is much more robust than explicit differentiation of the eigendecomposition.
Our method has better convergence properties and yields state-of-the-art results.
arXiv Detail & Related papers (2020-04-15T04:29:34Z)
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.