paper-with-me

홈 › Papers

Evaluating generative networks using Gaussian mixtures of image features

2021-10-08 · Lorenzo Luzi, Carlos Ortiz Marrero, Nile Wynar, Richard G. Baraniuk, Michael J. Henry

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.

📄 PDF Abstract BibTeX arXiv:2110.05240

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Average Pooling 설명 없음
Inception-v3 Module Inception-v3 Module is an image block used in the Inception-v3 architecture. This architecture is used on the coarsest (8 ×…
Auxiliary Classifier Auxiliary Classifiers are type of architectural component that seek to improve the convergence of very deep networks. They are classifier heads we attach to layers before the…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Decentralized EM to Learn Gaussian Mixtures from Datasets Distributed by Features

2022-01-24 · Pedro Valdeira, Cláudia Soares, João Xavier

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 Learning

Refereeing the Referees: Evaluating Two-Sample Tests for Validating Generators in Precision Sciences

2024-09-24 · Samuele Grossi, Marco Letizia, Riccardo Torre

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 EfficiencySensitivity

Predicting Aircraft Trajectories: A Deep Generative Convolutional Recurrent Neural Networks Approach

2018-12-31 · Yulin Liu, Mark Hansen

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 Prediction

On Pooling-Based Track Fusion Strategies : Harmonic Mean Density

2024-12-09 · Nikhil Sharma, Shovan Bhaumik, Ratnasingham Tharmarasa, Thiagalingam Kirubarajan

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 Fusion

Support-Conditioned Flow Matching Is Kernel Smoothing

2026-05-13 · Daniel Matsui Smola arxiv

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…