Gaussian Latent Representations for Uncertainty Estimation using Mahalanobis Distance in Deep Classifiers

• URL: http://arxiv.org/abs/2305.13849v3
• Date: Fri, 29 Sep 2023 16:07:44 GMT
• Title: Gaussian Latent Representations for Uncertainty Estimation using Mahalanobis Distance in Deep Classifiers
• Authors: Aishwarya Venkataramanan, Assia Benbihi, Martin Laviale, Cedric Pradalier
• Abstract summary: We present a lightweight, fast, and high-performance regularization method for Mahalanobis distance-based uncertainty prediction. We show the applicability of our method to a real-life computer vision use case on microorganism classification.
• Score: 1.5088605208312555
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent works show that the data distribution in a network's latent space is useful for estimating classification uncertainty and detecting Out-of-distribution (OOD) samples. To obtain a well-regularized latent space that is conducive for uncertainty estimation, existing methods bring in significant changes to model architectures and training procedures. In this paper, we present a lightweight, fast, and high-performance regularization method for Mahalanobis distance-based uncertainty prediction, and that requires minimal changes to the network's architecture. To derive Gaussian latent representation favourable for Mahalanobis Distance calculation, we introduce a self-supervised representation learning method that separates in-class representations into multiple Gaussians. Classes with non-Gaussian representations are automatically identified and dynamically clustered into multiple new classes that are approximately Gaussian. Evaluation on standard OOD benchmarks shows that our method achieves state-of-the-art results on OOD detection with minimal inference time, and is very competitive on predictive probability calibration. Finally, we show the applicability of our method to a real-life computer vision use case on microorganism classification.

Related papers

• Towards Robust and Interpretable EMG-based Hand Gesture Recognition using Deep Metric Meta Learning [37.21211404608413]
  We propose a shift to deep metric-based meta-learning in EMG PR to supervise the creation of meaningful and interpretable representations. We derive a robust class proximity-based confidence estimator that leads to a better rejection of incorrect decisions.
  arXiv  Detail & Related papers  (2024-04-17T23:37:50Z)
• Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning [55.75959755058356]
  In deep reinforcement learning, estimating the value function is essential to evaluate the quality of states and actions. A recent study suggested that the error distribution for training the value function is often skewed because of the properties of the Bellman operator. We proposed a method called Symmetric Q-learning, in which the synthetic noise generated from a zero-mean distribution is added to the target values to generate a Gaussian error distribution.
  arXiv  Detail & Related papers  (2024-03-12T14:49:19Z)
• Variational Classification [51.2541371924591]
  We derive a variational objective to train the model, analogous to the evidence lower bound (ELBO) used to train variational auto-encoders. Treating inputs to the softmax layer as samples of a latent variable, our abstracted perspective reveals a potential inconsistency. We induce a chosen latent distribution, instead of the implicit assumption found in a standard softmax layer.
  arXiv  Detail & Related papers  (2023-05-17T17:47:19Z)
• Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentation [0.43512163406552007]
  We present a method for obtaining uncertainty scores from pixel-wise loss gradients which can be computed efficiently during inference. Our experiments show the ability of our method to identify wrong pixel classifications and to estimate prediction quality at negligible computational overhead.
  arXiv  Detail & Related papers  (2023-03-13T08:37:59Z)
• Transfer Learning Gaussian Anomaly Detection by Fine-Tuning Representations [3.5031508291335625]
  catastrophic forgetting prevents the successful fine-tuning of pre-trained representations on new datasets. We propose a new method to fine-tune learned representations for AD in a transfer learning setting. We additionally propose to use augmentations commonly employed for vicinal risk in a validation scheme to detect onset of catastrophic forgetting.
  arXiv  Detail & Related papers  (2021-08-09T15:29:04Z)
• On the Practicality of Deterministic Epistemic Uncertainty [106.06571981780591]
  deterministic uncertainty methods (DUMs) achieve strong performance on detecting out-of-distribution data. It remains unclear whether DUMs are well calibrated and can seamlessly scale to real-world applications.
  arXiv  Detail & Related papers  (2021-07-01T17:59:07Z)
• Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning [78.83598532168256]
  Marginal-likelihood based model-selection is rarely used in deep learning due to estimation difficulties. Our work shows that marginal likelihoods can improve generalization and be useful when validation data is unavailable.
  arXiv  Detail & Related papers  (2021-04-11T09:50:24Z)
• Remaining Useful Life Estimation Under Uncertainty with Causal GraphNets [0.0]
  A novel approach for the construction and training of time series models is presented. The proposed method is appropriate for constructing predictive models for non-stationary time series.
  arXiv  Detail & Related papers  (2020-11-23T21:28:03Z)
• Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier [68.38233199030908]
  Long-tail recognition tackles the natural non-uniformly distributed data in realworld scenarios. While moderns perform well on populated classes, its performance degrades significantly on tail classes. Deep-RTC is proposed as a new solution to the long-tail problem, combining realism with hierarchical predictions.
  arXiv  Detail & Related papers  (2020-07-20T05:57:42Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)

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.