Quantifying the uncertainty of model-based synthetic image quality metrics

• URL: http://arxiv.org/abs/2504.03623v1
• Date: Fri, 04 Apr 2025 17:41:58 GMT
• Title: Quantifying the uncertainty of model-based synthetic image quality metrics
• Authors: Ciaran Bench, Spencer A. Thomas,
• Abstract summary: Uncertainty quantification (UQ) is used to provide a measure of the trustworthiness of the feature embedding model and an FID-like metric called the Fr'echet Autoencoder Distance (FAED)<n>We express uncertainty as the predictive variance of the embeddings as well as the standard deviation of the computed FAED values.<n>We find that their magnitude correlates with the extent to which the inputs are out-of-distribution to the model's training data, providing some validation of its ability to assess the trustworthiness of the FAED.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The quality of synthetically generated images (e.g. those produced by diffusion models) are often evaluated using information about image contents encoded by pretrained auxiliary models. For example, the Fr\'{e}chet Inception Distance (FID) uses embeddings from an InceptionV3 model pretrained to classify ImageNet. The effectiveness of this feature embedding model has considerable impact on the trustworthiness of the calculated metric (affecting its suitability in several domains, including medical imaging). Here, uncertainty quantification (UQ) is used to provide a heuristic measure of the trustworthiness of the feature embedding model and an FID-like metric called the Fr\'{e}chet Autoencoder Distance (FAED). We apply Monte Carlo dropout to a feature embedding model (convolutional autoencoder) to model the uncertainty in its embeddings. The distribution of embeddings for each input are then used to compute a distribution of FAED values. We express uncertainty as the predictive variance of the embeddings as well as the standard deviation of the computed FAED values. We find that their magnitude correlates with the extent to which the inputs are out-of-distribution to the model's training data, providing some validation of its ability to assess the trustworthiness of the FAED.

Related papers

• Sensitivity Analysis of Image Classification Models using Generalized Polynomial Chaos [0.0]
  This work investigates the sensitivity of image classification models used for predictive quality.<n>We propose modeling the distributional domain shifts of inputs with random variables and quantifying their impact on the model's outputs.
  arXiv  Detail & Related papers  (2025-06-23T15:22:31Z)
• A Meaningful Perturbation Metric for Evaluating Explainability Methods [55.09730499143998]
  We introduce a novel approach, which harnesses image generation models to perform targeted perturbation. Specifically, we focus on inpainting only the high-relevance pixels of an input image to modify the model's predictions while preserving image fidelity. This is in contrast to existing approaches, which often produce out-of-distribution modifications, leading to unreliable results.
  arXiv  Detail & Related papers  (2025-04-09T11:46:41Z)
• Model Integrity when Unlearning with T2I Diffusion Models [11.321968363411145]
  We propose approximate Machine Unlearning algorithms to reduce the generation of specific types of images, characterized by samples from a forget distribution'' We then propose unlearning algorithms that demonstrate superior effectiveness in preserving model integrity compared to existing baselines.
  arXiv  Detail & Related papers  (2024-11-04T13:15:28Z)
• Influence Functions for Scalable Data Attribution in Diffusion Models [52.92223039302037]
  Diffusion models have led to significant advancements in generative modelling.<n>Yet their widespread adoption poses challenges regarding data attribution and interpretability.<n>We develop an influence functions framework to address these challenges.
  arXiv  Detail & Related papers  (2024-10-17T17:59:02Z)
• Rethinking interpretation: Input-agnostic saliency mapping of deep visual classifiers [28.28834523468462]
  Saliency methods provide post-hoc model interpretation by attributing input features to the model outputs. We show that input-specific saliency mapping is intrinsically susceptible to misleading feature attribution. We introduce a new perspective of input-agnostic saliency mapping that computationally estimates the high-level features attributed by the model to its outputs.
  arXiv  Detail & Related papers  (2023-03-31T06:58:45Z)
• Masked Images Are Counterfactual Samples for Robust Fine-tuning [77.82348472169335]
  Fine-tuning deep learning models can lead to a trade-off between in-distribution (ID) performance and out-of-distribution (OOD) robustness. We propose a novel fine-tuning method, which uses masked images as counterfactual samples that help improve the robustness of the fine-tuning model.
  arXiv  Detail & Related papers  (2023-03-06T11:51:28Z)
• Distributional Learning of Variational AutoEncoder: Application to Synthetic Data Generation [0.7614628596146602]
  We propose a new approach that expands the model capacity without sacrificing the computational advantages of the VAE framework. Our VAE model's decoder is composed of an infinite mixture of asymmetric Laplace distribution. We apply the proposed model to synthetic data generation, and particularly, our model demonstrates superiority in easily adjusting the level of data privacy.
  arXiv  Detail & Related papers  (2023-02-22T11:26:50Z)
• MDN-VO: Estimating Visual Odometry with Confidence [34.8860186009308]
  Visual Odometry (VO) is used in many applications including robotics and autonomous systems. We propose a deep learning-based VO model to estimate 6-DoF poses, as well as a confidence model for these estimates. Our experiments show that the proposed model exceeds state-of-the-art performance in addition to detecting failure cases.
  arXiv  Detail & Related papers  (2021-12-23T19:26:04Z)
• Low-rank Characteristic Tensor Density Estimation Part II: Compression and Latent Density Estimation [31.631861197477185]
  Learning generative probabilistic models is a core problem in machine learning. This paper proposes a joint dimensionality reduction and non-parametric density estimation framework. We demonstrate that the proposed model achieves very promising results on regression tasks, sampling, and anomaly detection.
  arXiv  Detail & Related papers  (2021-06-20T00:38:56Z)
• How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models [95.8037674226622]
  We introduce a 3-dimensional evaluation metric that characterizes the fidelity, diversity and generalization performance of any generative model in a domain-agnostic fashion. Our metric unifies statistical divergence measures with precision-recall analysis, enabling sample- and distribution-level diagnoses of model fidelity and diversity.
  arXiv  Detail & Related papers  (2021-02-17T18:25:30Z)
• Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning [123.3472310767721]
  Prediction credibility measures are fundamental in statistics and machine learning. These measures should account for the wide variety of models used in practice. The framework developed in this work expresses the credibility as a risk-fit trade-off.
  arXiv  Detail & Related papers  (2020-11-24T19:52:38Z)
• 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.