SIDDA: SInkhorn Dynamic Domain Adaptation for Image Classification with Equivariant Neural Networks

• URL: http://arxiv.org/abs/2501.14048v1
• Date: Thu, 23 Jan 2025 19:29:34 GMT
• Title: SIDDA: SInkhorn Dynamic Domain Adaptation for Image Classification with Equivariant Neural Networks
• Authors: Sneh Pandya, Purvik Patel, Brian D. Nord, Mike Walmsley, Aleksandra Ćiprijanović,
• Abstract summary: SIDDA is an out-of-the-box DA training algorithm built upon the Sinkhorn divergence. We find that SIDDA enhances the generalization capabilities of NNs. We also study the efficacy of SIDDA on ENNs with respect to the varying group orders of the dihedral group $D_N$.
• Score: 37.69303106863453
• License:
• Abstract: Modern neural networks (NNs) often do not generalize well in the presence of a "covariate shift"; that is, in situations where the training and test data distributions differ, but the conditional distribution of classification labels remains unchanged. In such cases, NN generalization can be reduced to a problem of learning more domain-invariant features. Domain adaptation (DA) methods include a range of techniques aimed at achieving this; however, these methods have struggled with the need for extensive hyperparameter tuning, which then incurs significant computational costs. In this work, we introduce SIDDA, an out-of-the-box DA training algorithm built upon the Sinkhorn divergence, that can achieve effective domain alignment with minimal hyperparameter tuning and computational overhead. We demonstrate the efficacy of our method on multiple simulated and real datasets of varying complexity, including simple shapes, handwritten digits, and real astronomical observations. SIDDA is compatible with a variety of NN architectures, and it works particularly well in improving classification accuracy and model calibration when paired with equivariant neural networks (ENNs). We find that SIDDA enhances the generalization capabilities of NNs, achieving up to a $\approx40\%$ improvement in classification accuracy on unlabeled target data. We also study the efficacy of DA on ENNs with respect to the varying group orders of the dihedral group $D_N$, and find that the model performance improves as the degree of equivariance increases. Finally, we find that SIDDA enhances model calibration on both source and target data--achieving over an order of magnitude improvement in the ECE and Brier score. SIDDA's versatility, combined with its automated approach to domain alignment, has the potential to advance multi-dataset studies by enabling the development of highly generalizable models.

Related papers

• Disentangling Masked Autoencoders for Unsupervised Domain Generalization [57.56744870106124]
  Unsupervised domain generalization is fast gaining attention but is still far from well-studied. Disentangled Masked Auto (DisMAE) aims to discover the disentangled representations that faithfully reveal intrinsic features. DisMAE co-trains the asymmetric dual-branch architecture with semantic and lightweight variation encoders.
  arXiv  Detail & Related papers  (2024-07-10T11:11:36Z)
• Improving SMOTE via Fusing Conditional VAE for Data-adaptive Noise Filtering [0.5735035463793009]
  We introduce a framework to enhance the SMOTE algorithm using Variational Autoencoders (VAE) Our approach systematically quantifies the density of data points in a low-dimensional latent space using the VAE, simultaneously incorporating information on class labels and classification difficulty. Empirical studies on several imbalanced datasets represent that this simple process innovatively improves the conventional SMOTE algorithm over the deep learning models.
  arXiv  Detail & Related papers  (2024-05-30T07:06:02Z)
• Deep Neural Network Models Trained With A Fixed Random Classifier Transfer Better Across Domains [23.10912424714101]
  Recently discovered Neural collapse (NC) phenomenon states that the last-layer weights of Deep Neural Networks converge to the so-called Equiangular Tight Frame (ETF) simplex, at the terminal phase of their training. Inspired by NC properties, we explore in this paper the transferability of DNN models trained with their last layer weight fixed according to ETF.
  arXiv  Detail & Related papers  (2024-02-28T15:52:30Z)
• Domain Adaptation Principal Component Analysis: base linear method for learning with out-of-distribution data [55.41644538483948]
  Domain adaptation is a popular paradigm in modern machine learning. We present a method called Domain Adaptation Principal Component Analysis (DAPCA) DAPCA finds a linear reduced data representation useful for solving the domain adaptation task.
  arXiv  Detail & Related papers  (2022-08-28T21:10:56Z)
• Domain Adaptive Nuclei Instance Segmentation and Classification via Category-aware Feature Alignment and Pseudo-labelling [65.40672505658213]
  We propose a novel deep neural network, namely Category-Aware feature alignment and Pseudo-Labelling Network (CAPL-Net) for UDA nuclei instance segmentation and classification. Our approach outperforms state-of-the-art UDA methods with a remarkable margin.
  arXiv  Detail & Related papers  (2022-07-04T07:05:06Z)
• Spatial Graph Convolutional Neural Network via Structured Subdomain Adaptation and Domain Adversarial Learning for Bearing Fault Diagnosis [0.0]
  Unsupervised domain adaptation (UDA) has shown remarkable results in bearing fault diagnosis under changing working conditions. This paper addresses mentioned challenges by presenting the novel deep subdomain adaptation graph convolution neural network (DSAGCN) It has two key characteristics: First, graph convolution neural network (GCNN) is employed to model the structure of data.
  arXiv  Detail & Related papers  (2021-12-11T17:34:36Z)
• Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder [23.860842627883187]
  We teach the model to capture broader variations of the feature distributions with a novel noise-enhanced supervised autoencoder (NSAE) NSAE trains the model by jointly reconstructing inputs and predicting the labels of inputs as well as their reconstructed pairs. We also take advantage of NSAE structure and propose a two-step fine-tuning procedure that achieves better adaption and improves classification performance in the target domain.
  arXiv  Detail & Related papers  (2021-08-11T04:45:56Z)
• Understanding Overparameterization in Generative Adversarial Networks [56.57403335510056]
  Generative Adversarial Networks (GANs) are used to train non- concave mini-max optimization problems. A theory has shown the importance of the gradient descent (GD) to globally optimal solutions. We show that in an overized GAN with a $1$-layer neural network generator and a linear discriminator, the GDA converges to a global saddle point of the underlying non- concave min-max problem.
  arXiv  Detail & Related papers  (2021-04-12T16:23:37Z)
• Dynamic Domain Adaptation for Efficient Inference [12.713628738434881]
  Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain. Most prior DA approaches leverage complicated and powerful deep neural networks to improve the adaptation capacity. We propose a dynamic domain adaptation (DDA) framework, which can simultaneously achieve efficient target inference in low-resource scenarios.
  arXiv  Detail & Related papers  (2021-03-26T08:53:16Z)
• Self-Guided Adaptation: Progressive Representation Alignment for Domain Adaptive Object Detection [86.69077525494106]
  Unsupervised domain adaptation (UDA) has achieved unprecedented success in improving the cross-domain robustness of object detection models. Existing UDA methods largely ignore the instantaneous data distribution during model learning, which could deteriorate the feature representation given large domain shift. We propose a Self-Guided Adaptation (SGA) model, target at aligning feature representation and transferring object detection models across domains.
  arXiv  Detail & Related papers  (2020-03-19T13:30:45Z)

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.