Evaluating generative networks using Gaussian mixtures of image features
We develop a measure for evaluating the performance of generative networks given two sets of images. A popular performance measure currently used to do this is the Fr\'echet Inception Distance (FID). FID assumes that images featurized using the penultimate layer of Inception-v3 follow a Gaussian distribution, an assumption which cannot be violated if we wish to use FID as a metric. However, we show that Inception-v3 features of the ImageNet dataset are not Gaussian; in particular, every single marginal is not Gaussian. To remedy this problem, we model the featurized images using Gaussian mixture models (GMMs) and compute the 2-Wasserstein distance restricted to GMMs. We define a performance measure, which we call WaM, on two sets of images by using Inception-v3 (or another classifier) to featurize the images, estimate two GMMs, and use the restricted $2$-Wasserstein distance to compare the GMMs. We experimentally show the advantages of WaM over FID, including how FID is more sensitive than WaM to imperceptible image perturbations. By modelling the non-Gaussian features obtained from Inception-v3 as GMMs and using a GMM metric, we can more accurately evaluate generative network performance.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Decentralized EM to Learn Gaussian Mixtures from Datasets Distributed by Features
Expectation Maximization (EM) is the standard method to learn Gaussian mixtures. Yet its classic, centralized form is often infeasible, due to privacy concerns and computational and communication bottlenecks. Prior work …
Federated LearningRefereeing the Referees: Evaluating Two-Sample Tests for Validating Generators in Precision Sciences
We propose a robust methodology to evaluate the performance and computational efficiency of non-parametric two-sample tests, specifically designed for high-dimensional generative models in scientific applications such as…
Computational EfficiencySensitivityPredicting Aircraft Trajectories: A Deep Generative Convolutional Recurrent Neural Networks Approach
Reliable 4D aircraft trajectory prediction, whether in a real-time setting or for analysis of counterfactuals, is important to the efficiency of the aviation system. Toward this end, we first propose a highly generalizab…
DecoderTrajectory PredictionOn Pooling-Based Track Fusion Strategies : Harmonic Mean Density
In a distributed sensor fusion architecture, using standard Kalman filter (naive fusion) can lead to degraded results as track correlations are ignored and conservative fusion strategies are employed as a sub-optimal alt…
Sensor FusionSupport-Conditioned Flow Matching Is Kernel Smoothing
Generative models are often conditioned on a small set of examples via cross-attention. Under the Gaussian optimal-transport path, we show that the exact velocity field induced by a finite support set is a Nadaraya--Wats…