Phase Matching for Out-of-Distribution Generalization
- URL: http://arxiv.org/abs/2307.12622v5
- Date: Fri, 15 Sep 2023 09:11:34 GMT
- Title: Phase Matching for Out-of-Distribution Generalization
- Authors: Chengming Hu, Yeqian Du, Rui Wang, Hao Chen
- Abstract summary: We introduce a structural causal model which interprets the phase spectrum as semi-causal factors and the amplitude spectrum as non-causal factors.
Our method introduces perturbations on the amplitude spectrum and establishes spatial relationships to match the phase components.
- Score: 9.03228987290643
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The Fourier transform, serving as an explicit decomposition method for visual
signals, has been employed to explain the out-of-distribution generalization
behaviors of Convolutional Neural Networks (CNNs). Previous studies have
indicated that the amplitude spectrum is susceptible to the disturbance caused
by distribution shifts. On the other hand, the phase spectrum preserves
highly-structured spatial information, which is crucial for robust visual
representation learning. However, the spatial relationships of phase spectrum
remain unexplored in previous research. In this paper, we aim to clarify the
relationships between Domain Generalization (DG) and the frequency components,
and explore the spatial relationships of the phase spectrum. Specifically, we
first introduce a Fourier-based structural causal model which interprets the
phase spectrum as semi-causal factors and the amplitude spectrum as non-causal
factors. Then, we propose Phase Matching (PhaMa) to address DG problems. Our
method introduces perturbations on the amplitude spectrum and establishes
spatial relationships to match the phase components. Through experiments on
multiple benchmarks, we demonstrate that our proposed method achieves
state-of-the-art performance in domain generalization and out-of-distribution
robustness tasks.
Related papers
- Measurement-Induced Spectral Transition [0.0]
noisy quantum dynamics exposed to weak measurements exhibit a spectral transition between gapless and gapped phases.
We show that the gapless and gapped phases respectively correspond to the volume-law and area-law phases of the entanglement entropy for the dominant Lyapunov vector.
arXiv Detail & Related papers (2024-06-26T10:33:28Z) - HoloNets: Spectral Convolutions do extend to Directed Graphs [59.851175771106625]
Conventional wisdom dictates that spectral convolutional networks may only be deployed on undirected graphs.
Here we show this traditional reliance on the graph Fourier transform to be superfluous.
We provide a frequency-response interpretation of newly developed filters, investigate the influence of the basis used to express filters and discuss the interplay with characteristic operators on which networks are based.
arXiv Detail & Related papers (2023-10-03T17:42:09Z) - Hodge-Aware Contrastive Learning [101.56637264703058]
Simplicial complexes prove effective in modeling data with multiway dependencies.
We develop a contrastive self-supervised learning approach for processing simplicial data.
arXiv Detail & Related papers (2023-09-14T00:40:07Z) - Exploring Invariant Representation for Visible-Infrared Person
Re-Identification [77.06940947765406]
Cross-spectral person re-identification, which aims to associate identities to pedestrians across different spectra, faces a main challenge of the modality discrepancy.
In this paper, we address the problem from both image-level and feature-level in an end-to-end hybrid learning framework named robust feature mining network (RFM)
Experiment results on two standard cross-spectral person re-identification datasets, RegDB and SYSU-MM01, have demonstrated state-of-the-art performance.
arXiv Detail & Related papers (2023-02-02T05:24:50Z) - Robust, Nonparametric, Efficient Decomposition of Spectral Peaks under
Distortion and Interference [0.0]
We propose a decomposition method for the spectral peaks in an observed frequency spectrum, which is efficiently acquired by utilizing the Fast Fourier Transform.
We model the peaks in spectrum as pseudo-symmetric functions, where the only constraint is a nonincreasing behavior around a central frequency when the distance increases.
Our approach is more robust against arbitrary distortion, interference and noise on the spectrum that may be caused by an observation system.
arXiv Detail & Related papers (2022-04-18T17:08:37Z) - Time-inhomogeneous diffusion geometry and topology [69.55228523791897]
Diffusion condensation is a time-inhomogeneous process where each step first computes and then applies a diffusion operator to the data.
We theoretically analyze the convergence and evolution of this process from geometric, spectral, and topological perspectives.
Our work gives theoretical insights into the convergence of diffusion condensation, and shows that it provides a link between topological and geometric data analysis.
arXiv Detail & Related papers (2022-03-28T16:06:17Z) - Spectral-Spatial Global Graph Reasoning for Hyperspectral Image
Classification [50.899576891296235]
Convolutional neural networks have been widely applied to hyperspectral image classification.
Recent methods attempt to address this issue by performing graph convolutions on spatial topologies.
arXiv Detail & Related papers (2021-06-26T06:24:51Z) - A Fourier-based Framework for Domain Generalization [82.54650565298418]
Domain generalization aims at tackling this problem by learning transferable knowledge from multiple source domains in order to generalize to unseen target domains.
This paper introduces a novel Fourier-based perspective for domain generalization.
Experiments on three benchmarks have demonstrated that the proposed method is able to achieve state-of-the-arts performance for domain generalization.
arXiv Detail & Related papers (2021-05-24T06:50:30Z) - Interpreting Stellar Spectra with Unsupervised Domain Adaptation [0.0]
We show how it is possible to transfer between simulated and observed domains.
Driven by an application to interpret stellar spectroscopic sky surveys, we construct the domain transfer pipeline.
arXiv Detail & Related papers (2020-07-06T23:09:13Z)
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.