TREND: Truncated Generalized Normal Density Estimation of Inception
Embeddings for Accurate GAN Evaluation
- URL: http://arxiv.org/abs/2104.14767v1
- Date: Fri, 30 Apr 2021 05:51:07 GMT
- Title: TREND: Truncated Generalized Normal Density Estimation of Inception
Embeddings for Accurate GAN Evaluation
- Authors: Junghyuk Lee and Jong-Seok Lee
- Abstract summary: Frech'et Inception distance is one of the most widely used metrics for evaluation of GANs.
We argue that this is an over-simplified assumption, which may lead to unreliable evaluation results.
We propose a novel metric for accurate evaluation of GANs, named TREND (TRuncated gEneralized Normal Density estimation of inception embeddings)
- Score: 27.80517509528215
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Evaluating image generation models such as generative adversarial networks
(GANs) is a challenging problem. A common approach is to compare the
distributions of the set of ground truth images and the set of generated test
images. The Frech\'et Inception distance is one of the most widely used metrics
for evaluation of GANs, which assumes that the features from a trained
Inception model for a set of images follow a normal distribution. In this
paper, we argue that this is an over-simplified assumption, which may lead to
unreliable evaluation results, and more accurate density estimation can be
achieved using a truncated generalized normal distribution. Based on this, we
propose a novel metric for accurate evaluation of GANs, named TREND (TRuncated
gEneralized Normal Density estimation of inception embeddings). We demonstrate
that our approach significantly reduces errors of density estimation, which
consequently eliminates the risk of faulty evaluation results. Furthermore, we
show that the proposed metric significantly improves robustness of evaluation
results against variation of the number of image samples.
Related papers
- GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection [60.78684630040313]
Diffusion models tend to reconstruct normal counterparts of test images with certain noises added.
From the global perspective, the difficulty of reconstructing images with different anomalies is uneven.
We propose a global and local adaptive diffusion model (abbreviated to GLAD) for unsupervised anomaly detection.
arXiv Detail & Related papers (2024-06-11T17:27:23Z) - Overcoming Saturation in Density Ratio Estimation by Iterated Regularization [11.244546184962996]
We show that a class of kernel methods for density ratio estimation suffers from error saturation.
We introduce iterated regularization in density ratio estimation to achieve fast error rates.
arXiv Detail & Related papers (2024-02-21T16:02:14Z) - Projection Regret: Reducing Background Bias for Novelty Detection via
Diffusion Models [72.07462371883501]
We propose emphProjection Regret (PR), an efficient novelty detection method that mitigates the bias of non-semantic information.
PR computes the perceptual distance between the test image and its diffusion-based projection to detect abnormality.
Extensive experiments demonstrate that PR outperforms the prior art of generative-model-based novelty detection methods by a significant margin.
arXiv Detail & Related papers (2023-12-05T09:44:47Z) - Uncertainty Inspired Underwater Image Enhancement [45.05141499761876]
We present a novel probabilistic network to learn the enhancement distribution of degraded underwater images.
By learning the enhancement distribution, our method can cope with the bias introduced in the reference map labeling.
Experimental results demonstrate that our approach enables sampling possible enhancement predictions.
arXiv Detail & Related papers (2022-07-20T06:42:28Z) - Out-of-Distribution Detection with Class Ratio Estimation [4.930817402876787]
Density-based Out-of-distribution (OOD) detection has recently been shown unreliable for the task of detecting OOD images.
We propose to unify density ratio based methods under a novel framework that builds energy-based models and employs differing base distributions.
arXiv Detail & Related papers (2022-06-08T15:20:49Z) - On Variance Estimation of Random Forests [0.0]
This paper develops an unbiased variance estimator based on incomplete U-statistics.
We show that our estimators enjoy lower bias and more accurate confidence interval coverage without additional computational costs.
arXiv Detail & Related papers (2022-02-18T03:35:47Z) - Robust Estimation for Nonparametric Families via Generative Adversarial
Networks [92.64483100338724]
We provide a framework for designing Generative Adversarial Networks (GANs) to solve high dimensional robust statistics problems.
Our work extend these to robust mean estimation, second moment estimation, and robust linear regression.
In terms of techniques, our proposed GAN losses can be viewed as a smoothed and generalized Kolmogorov-Smirnov distance.
arXiv Detail & Related papers (2022-02-02T20:11:33Z) - Deblurring via Stochastic Refinement [85.42730934561101]
We present an alternative framework for blind deblurring based on conditional diffusion models.
Our method is competitive in terms of distortion metrics such as PSNR.
arXiv Detail & Related papers (2021-12-05T04:36:09Z) - Low-Light Image Enhancement with Normalizing Flow [92.52290821418778]
In this paper, we investigate to model this one-to-many relationship via a proposed normalizing flow model.
An invertible network that takes the low-light images/features as the condition and learns to map the distribution of normally exposed images into a Gaussian distribution.
The experimental results on the existing benchmark datasets show our method achieves better quantitative and qualitative results, obtaining better-exposed illumination, less noise and artifact, and richer colors.
arXiv Detail & Related papers (2021-09-13T12:45:08Z) - Unsupervised Lesion Detection via Image Restoration with a Normative
Prior [6.495883501989547]
We propose a probabilistic model that uses a network-based prior as the normative distribution and detect lesions pixel-wise using MAP estimation.
Experiments with gliomas and stroke lesions in brain MRI show that the proposed approach outperforms the state-of-the-art unsupervised methods by a substantial margin.
arXiv Detail & Related papers (2020-04-30T18:03:18Z) - TraDE: Transformers for Density Estimation [101.20137732920718]
TraDE is a self-attention-based architecture for auto-regressive density estimation.
We present a suite of tasks such as regression using generated samples, out-of-distribution detection, and robustness to noise in the training data.
arXiv Detail & Related papers (2020-04-06T07:32:51Z)
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.