Self-supervised learning with rotation-invariant kernels

• URL: http://arxiv.org/abs/2208.00789v1
• Date: Thu, 28 Jul 2022 08:06:24 GMT
• Title: Self-supervised learning with rotation-invariant kernels
• Authors: L\'eon Zheng (DANTE), Gilles Puy, Elisa Riccietti (DANTE), Patrick P\'erez, R\'emi Gribonval (DANTE)
• Abstract summary: We propose a general kernel framework to design a generic regularization loss that promotes the embedding distribution to be close to the uniform distribution on the hypersphere. Our framework uses rotation-invariant kernels defined on the hypersphere, also known as dot-product kernels. Our experiments demonstrate that using a truncated rotation-invariant kernel provides competitive results compared to state-of-the-art methods.
• Score: 4.059849656394191
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A major paradigm for learning image representations in a self-supervised manner is to learn a model that is invariant to some predefined image transformations (cropping, blurring, color jittering, etc.), while regularizing the embedding distribution to avoid learning a degenerate solution. Our first contribution is to propose a general kernel framework to design a generic regularization loss that promotes the embedding distribution to be close to the uniform distribution on the hypersphere, with respect to the maximum mean discrepancy pseudometric. Our framework uses rotation-invariant kernels defined on the hypersphere, also known as dot-product kernels. Our second contribution is to show that this flexible kernel approach encompasses several existing self-supervised learning methods, including uniformity-based and information-maximization methods. Finally, by exploring empirically several kernel choices, our experiments demonstrate that using a truncated rotation-invariant kernel provides competitive results compared to state-of-the-art methods, and we show practical situations where our method benefits from the kernel trick to reduce computational complexity.

Related papers

• Learning to Embed Distributions via Maximum Kernel Entropy [0.0]
  Emprimiical data can often be considered as samples from a set of probability distributions. Kernel methods have emerged as a natural approach for learning to classify these distributions. We propose a novel objective for the unsupervised learning of data-dependent distribution kernel.
  arXiv  Detail & Related papers  (2024-08-01T13:34:19Z)
• Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysis [28.18800845199871]
  We present a novel non-rigid point set registration method inspired by unsupervised clustering analysis. Our method achieves high accuracy results across various scenarios and surpasses competitors by a significant margin.
  arXiv  Detail & Related papers  (2024-06-27T01:16:44Z)
• A Unified Theory of Stochastic Proximal Point Methods without Smoothness [52.30944052987393]
  Proximal point methods have attracted considerable interest owing to their numerical stability and robustness against imperfect tuning. This paper presents a comprehensive analysis of a broad range of variations of the proximal point method (SPPM)
  arXiv  Detail & Related papers  (2024-05-24T21:09:19Z)
• Improved learning theory for kernel distribution regression with two-stage sampling [3.154269505086155]
  kernel methods have become a method of choice to tackle the distribution regression problem. We introduce the novel near-unbiased condition on the Hilbertian embeddings, that enables us to provide new error bounds. We show that this near-unbiased condition holds for three important classes of kernels, based on optimal transport and mean embedding.
  arXiv  Detail & Related papers  (2023-08-28T06:29:09Z)
• An Online Multiple Kernel Parallelizable Learning Scheme [6.436174170552483]
  We propose a learning scheme that scalably combines several single kernel-based online methods to reduce the kernel-selection bias. The proposed learning scheme applies to any task formulated as a regularized empirical risk minimization convex problem.
  arXiv  Detail & Related papers  (2023-08-19T20:15:02Z)
• Dynamic Kernel-Based Adaptive Spatial Aggregation for Learned Image Compression [63.56922682378755]
  We focus on extending spatial aggregation capability and propose a dynamic kernel-based transform coding. The proposed adaptive aggregation generates kernel offsets to capture valid information in the content-conditioned range to help transform. Experimental results demonstrate that our method achieves superior rate-distortion performance on three benchmarks compared to the state-of-the-art learning-based methods.
  arXiv  Detail & Related papers  (2023-08-17T01:34:51Z)
• Variational Autoencoder Kernel Interpretation and Selection for Classification [59.30734371401315]
  This work proposed kernel selection approaches for probabilistic classifiers based on features produced by the convolutional encoder of a variational autoencoder. In the proposed implementation, each latent variable was sampled from the distribution associated with a single kernel of the last encoder's convolution layer, as an individual distribution was created for each kernel. choosing relevant features on the sampled latent variables makes it possible to perform kernel selection, filtering the uninformative features and kernels.
  arXiv  Detail & Related papers  (2022-09-10T17:22:53Z)
• On the Benefits of Large Learning Rates for Kernel Methods [110.03020563291788]
  We show that a phenomenon can be precisely characterized in the context of kernel methods. We consider the minimization of a quadratic objective in a separable Hilbert space, and show that with early stopping, the choice of learning rate influences the spectral decomposition of the obtained solution.
  arXiv  Detail & Related papers  (2022-02-28T13:01:04Z)
• Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition [54.07797071198249]
  We introduce a new scalable variational Gaussian process approximation which provides a high fidelity approximation while retaining general applicability. We demonstrate that, on a range of regression and classification problems, our approach can exploit input space symmetries such as translations and reflections. Notably, our approach achieves state-of-the-art results on CIFAR-10 among pure GP models.
  arXiv  Detail & Related papers  (2021-06-10T18:17:57Z)
• Flow-based Kernel Prior with Application to Blind Super-Resolution [143.21527713002354]
  Kernel estimation is generally one of the key problems for blind image super-resolution (SR) This paper proposes a normalizing flow-based kernel prior (FKP) for kernel modeling. Experiments on synthetic and real-world images demonstrate that the proposed FKP can significantly improve the kernel estimation accuracy.
  arXiv  Detail & Related papers  (2021-03-29T22:37:06Z)
• Towards a Unified Quadrature Framework for Large-Scale Kernel Machines [35.32894170512829]
  We develop a quadrature framework for large-scale kernel machines via a numerical integration representation. We leverage fully symmetric interpolatory rules to efficiently compute quadrature nodes and associated weights for kernel approximation.
  arXiv  Detail & Related papers  (2020-11-03T12:48:07Z)

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.