Test-Time Augmentation Meets Variational Bayes

• URL: http://arxiv.org/abs/2409.12587v1
• Date: Thu, 19 Sep 2024 09:11:01 GMT
• Title: Test-Time Augmentation Meets Variational Bayes
• Authors: Masanari Kimura, Howard Bondell,
• Abstract summary: Test-Time Augmentation (TTA) is a technique that instead leverages data augmentations during the testing phase to achieve robust predictions. In this study, we consider a weighted version of the TTA based on the contribution of each data augmentation. We also show that optimizing the weights to maximize the marginal log-likelihood suppresses candidates of unwanted data augmentations at the test phase.
• Score: 0.951494089949975
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Data augmentation is known to contribute significantly to the robustness of machine learning models. In most instances, data augmentation is utilized during the training phase. Test-Time Augmentation (TTA) is a technique that instead leverages these data augmentations during the testing phase to achieve robust predictions. More precisely, TTA averages the predictions of multiple data augmentations of an instance to produce a final prediction. Although the effectiveness of TTA has been empirically reported, it can be expected that the predictive performance achieved will depend on the set of data augmentation methods used during testing. In particular, the data augmentation methods applied should make different contributions to performance. That is, it is anticipated that there may be differing degrees of contribution in the set of data augmentation methods used for TTA, and these could have a negative impact on prediction performance. In this study, we consider a weighted version of the TTA based on the contribution of each data augmentation. Some variants of TTA can be regarded as considering the problem of determining the appropriate weighting. We demonstrate that the determination of the coefficients of this weighted TTA can be formalized in a variational Bayesian framework. We also show that optimizing the weights to maximize the marginal log-likelihood suppresses candidates of unwanted data augmentations at the test phase.

Related papers

• AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation [7.079932622432037]
  Test-time adaptation (TTA) has emerged as a viable solution to adapt pre-trained models to domain shifts using unlabeled test data. We propose AETTA, a label-free accuracy estimation algorithm for TTA. We show that AETTA shows an average of 19.8%p more accurate estimation compared with the baselines.
  arXiv  Detail & Related papers  (2024-04-01T04:21:49Z)
• Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting [55.17761802332469]
  Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and test data by adapting a given model w.r.t. any test sample. Prior methods perform backpropagation for each test sample, resulting in unbearable optimization costs to many applications. We propose an Efficient Anti-Forgetting Test-Time Adaptation (EATA) method which develops an active sample selection criterion to identify reliable and non-redundant samples.
  arXiv  Detail & Related papers  (2024-03-18T05:49:45Z)
• Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors [36.54076844195179]
  Test-time adaptation (TTA) fine-tunes pre-trained deep neural networks for unseen test data. We introduce a novel TTA method named Destroy Your Object (DeYO)
  arXiv  Detail & Related papers  (2024-03-12T07:01:57Z)
• TEA: Test-time Energy Adaptation [67.4574269851666]
  Test-time adaptation (TTA) aims to improve model generalizability when test data diverges from training distribution. We propose a novel energy-based perspective, enhancing the model's perception of target data distributions.
  arXiv  Detail & Related papers  (2023-11-24T10:49:49Z)
• Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning [73.75282761503581]
  We propose DiffTPT, which leverages pre-trained diffusion models to generate diverse and informative new data. Our experiments on test datasets with distribution shifts and unseen categories demonstrate that DiffTPT improves the zero-shot accuracy by an average of 5.13%.
  arXiv  Detail & Related papers  (2023-08-11T09:36:31Z)
• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts [143.14128737978342]
  Test-time adaptation, an emerging paradigm, has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions. Recent progress in this paradigm highlights the significant benefits of utilizing unlabeled data for training self-adapted models prior to inference.
  arXiv  Detail & Related papers  (2023-03-27T16:32:21Z)
• Robust Continual Test-time Adaptation: Instance-aware BN and Prediction-balanced Memory [58.72445309519892]
  We present a new test-time adaptation scheme that is robust against non-i.i.d. test data streams. Our novelty is mainly two-fold: (a) Instance-Aware Batch Normalization (IABN) that corrects normalization for out-of-distribution samples, and (b) Prediction-balanced Reservoir Sampling (PBRS) that simulates i.i.d. data stream from non-i.i.d. stream in a class-balanced manner.
  arXiv  Detail & Related papers  (2022-08-10T03:05:46Z)
• Improved Text Classification via Test-Time Augmentation [2.493374942115722]
  Test-time augmentation is an established technique to improve the performance of image classification models. We present augmentation policies that yield significant accuracy improvements with language models. Experiments across a binary classification task and dataset show that test-time augmentation can deliver consistent improvements.
  arXiv  Detail & Related papers  (2022-06-27T19:57:27Z)
• Augmentation-Aware Self-Supervision for Data-Efficient GAN Training [68.81471633374393]
  Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. We propose a novel augmentation-aware self-supervised discriminator that predicts the augmentation parameter of the augmented data. We compare our method with state-of-the-art (SOTA) methods using the class-conditional BigGAN and unconditional StyleGAN2 architectures.
  arXiv  Detail & Related papers  (2022-05-31T10:35:55Z)

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.