A Pragmatic Note on Evaluating Generative Models with Fréchet Inception Distance for Retinal Image Synthesis

• URL: http://arxiv.org/abs/2502.17160v2
• Date: Wed, 26 Feb 2025 16:03:19 GMT
• Title: A Pragmatic Note on Evaluating Generative Models with Fréchet Inception Distance for Retinal Image Synthesis
• Authors: Yuli Wu, Fucheng Liu, Rüveyda Yilmaz, Henning Konermann, Peter Walter, Johannes Stegmaier,
• Abstract summary: Fr'echet Inception Distance (FID), computed with an ImageNet pretrained Inception-v3 network, is widely used as a state-of-the-art evaluation metric for generative models.<n>In this paper, we examine cases from retinal imaging modalities, including color fundus photography and optical coherence tomography, where FID and its related metrics misalign with task-specific evaluation goals.
• Score: 1.2274782635747272
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fr\'echet Inception Distance (FID), computed with an ImageNet pretrained Inception-v3 network, is widely used as a state-of-the-art evaluation metric for generative models. It assumes that feature vectors from Inception-v3 follow a multivariate Gaussian distribution and calculates the 2-Wasserstein distance based on their means and covariances. While FID effectively measures how closely synthetic data match real data in many image synthesis tasks, the primary goal in biomedical generative models is often to enrich training datasets ideally with corresponding annotations. For this purpose, the gold standard for evaluating generative models is to incorporate synthetic data into downstream task training, such as classification and segmentation, to pragmatically assess its performance. In this paper, we examine cases from retinal imaging modalities, including color fundus photography and optical coherence tomography, where FID and its related metrics misalign with task-specific evaluation goals in classification and segmentation. We highlight the limitations of using various metrics, represented by FID and its variants, as evaluation criteria for these applications and address their potential caveats in broader biomedical imaging modalities and downstream tasks.

Related papers

• Analyzing the Feature Extractor Networks for Face Image Synthesis [0.0]
  This study investigates the behavior of diverse feature extractors -- InceptionV3, CLIP, DINOv2, and ArcFace -- considering a variety of metrics -- FID, KID, Precision&Recall. Experiments include deep-down analysis of the features: $L$ normalization, model attention during extraction, and domain distributions in the feature space.
  arXiv  Detail & Related papers  (2024-06-04T09:41:40Z)
• Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems [80.62854148838359]
  Eye image segmentation is a critical step in eye tracking that has great influence over the final gaze estimate. We use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data. Our methods result in robust, improved performance when tackling the discrepancy between simulation and real-world data samples.
  arXiv  Detail & Related papers  (2024-03-23T22:32:06Z)
• Interpretable 2D Vision Models for 3D Medical Images [47.75089895500738]
  This study proposes a simple approach of adapting 2D networks with an intermediate feature representation for processing 3D images. We show on all 3D MedMNIST datasets as benchmark and two real-world datasets consisting of several hundred high-resolution CT or MRI scans that our approach performs on par with existing methods.
  arXiv  Detail & Related papers  (2023-07-13T08:27:09Z)
• Revisiting the Evaluation of Image Synthesis with GANs [55.72247435112475]
  This study presents an empirical investigation into the evaluation of synthesis performance, with generative adversarial networks (GANs) as a representative of generative models. In particular, we make in-depth analyses of various factors, including how to represent a data point in the representation space, how to calculate a fair distance using selected samples, and how many instances to use from each set.
  arXiv  Detail & Related papers  (2023-04-04T17:54:32Z)
• MAUVE Scores for Generative Models: Theory and Practice [95.86006777961182]
  We present MAUVE, a family of comparison measures between pairs of distributions such as those encountered in the generative modeling of text or images. We find that MAUVE can quantify the gaps between the distributions of human-written text and those of modern neural language models. We demonstrate in the vision domain that MAUVE can identify known properties of generated images on par with or better than existing metrics.
  arXiv  Detail & Related papers  (2022-12-30T07:37:40Z)
• Stacking Ensemble Learning in Deep Domain Adaptation for Ophthalmic Image Classification [61.656149405657246]
  Domain adaptation is effective in image classification tasks where obtaining sufficient label data is challenging. We propose a novel method, named SELDA, for stacking ensemble learning via extending three domain adaptation methods. The experimental results using Age-Related Eye Disease Study (AREDS) benchmark ophthalmic dataset demonstrate the effectiveness of the proposed model.
  arXiv  Detail & Related papers  (2022-09-27T14:19:00Z)
• Pathology Synthesis of 3D-Consistent Cardiac MR Images using 2D VAEs and GANs [0.5039813366558306]
  We propose a method for generating labeled data for the application of supervised deep-learning (DL) training. The image synthesis consists of label deformation and label-to-image translation tasks. We demonstrate that such an approach could provide a solution to diversify and enrich an available database of cardiac MR images.
  arXiv  Detail & Related papers  (2022-09-09T10:17:49Z)
• Triple-View Feature Learning for Medical Image Segmentation [9.992387025633805]
  TriSegNet is a semi-supervised semantic segmentation framework. It uses triple-view feature learning on a limited amount of labelled data and a large amount of unlabeled data.
  arXiv  Detail & Related papers  (2022-08-12T14:41:40Z)
• Self-Paced Contrastive Learning for Semi-supervisedMedical Image Segmentation with Meta-labels [6.349708371894538]
  We propose to adapt contrastive learning to work with meta-label annotations. We use the meta-labels for pre-training the image encoder as well as to regularize a semi-supervised training. Results on three different medical image segmentation datasets show that our approach highly boosts the performance of a model trained on a few scans.
  arXiv  Detail & Related papers  (2021-07-29T04:30:46Z)
• Deep Co-Attention Network for Multi-View Subspace Learning [73.3450258002607]
  We propose a deep co-attention network for multi-view subspace learning. It aims to extract both the common information and the complementary information in an adversarial setting. In particular, it uses a novel cross reconstruction loss and leverages the label information to guide the construction of the latent representation.
  arXiv  Detail & Related papers  (2021-02-15T18:46:44Z)
• Graph Neural Networks for UnsupervisedDomain Adaptation of Histopathological ImageAnalytics [22.04114134677181]
  We present a novel method for the unsupervised domain adaptation for histological image analysis. It is based on a backbone for embedding images into a feature space, and a graph neural layer for propa-gating the supervision signals of images with labels. In experiments, our methodachieves state-of-the-art performance on four public datasets.
  arXiv  Detail & Related papers  (2020-08-21T04:53:44Z)
• Phase Consistent Ecological Domain Adaptation [76.75730500201536]
  We focus on the task of semantic segmentation, where annotated synthetic data are aplenty, but annotating real data is laborious. The first criterion, inspired by visual psychophysics, is that the map between the two image domains be phase-preserving. The second criterion aims to leverage ecological statistics, or regularities in the scene which are manifest in any image of it, regardless of the characteristics of the illuminant or the imaging sensor.
  arXiv  Detail & Related papers  (2020-04-10T06:58:03Z)

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.