Anomaly Score: Evaluating Generative Models and Individual Generated Images based on Complexity and Vulnerability

• URL: http://arxiv.org/abs/2312.10634v2
• Date: Tue, 9 Apr 2024 09:18:26 GMT
• Title: Anomaly Score: Evaluating Generative Models and Individual Generated Images based on Complexity and Vulnerability
• Authors: Jaehui Hwang, Junghyuk Lee, Jong-Seok Lee,
• Abstract summary: We investigate the relationship between the representation space and input space around generated images. We introduce a new metric to evaluating image-generative models called anomaly score (AS)
• Score: 21.355484227864466
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the advancement of generative models, the assessment of generated images becomes more and more important. Previous methods measure distances between features of reference and generated images from trained vision models. In this paper, we conduct an extensive investigation into the relationship between the representation space and input space around generated images. We first propose two measures related to the presence of unnatural elements within images: complexity, which indicates how non-linear the representation space is, and vulnerability, which is related to how easily the extracted feature changes by adversarial input changes. Based on these, we introduce a new metric to evaluating image-generative models called anomaly score (AS). Moreover, we propose AS-i (anomaly score for individual images) that can effectively evaluate generated images individually. Experimental results demonstrate the validity of the proposed approach.

Related papers

• Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection [106.39544368711427]
  We study the problem of generalizable synthetic image detection, aiming to detect forgery images from diverse generative methods. We present a novel forgery-aware adaptive transformer approach, namely FatFormer. Our approach tuned on 4-class ProGAN data attains an average of 98% accuracy to unseen GANs, and surprisingly generalizes to unseen diffusion models with 95% accuracy.
  arXiv  Detail & Related papers  (2023-12-27T17:36:32Z)
• AS-IntroVAE: Adversarial Similarity Distance Makes Robust IntroVAE [8.294692832460546]
  introspective models like IntroVAE and S-IntroVAE have excelled in image generation and reconstruction tasks. We propose a new variation of IntroVAE called Adversarial Similarity Distance Introspective Variational Autoencoder (AS-IntroVAE)
  arXiv  Detail & Related papers  (2022-06-28T11:40:17Z)
• Assessing a Single Image in Reference-Guided Image Synthesis [14.936460594115953]
  We propose a learning-based framework, Reference-guided Image Synthesis Assessment (RISA) to quantitatively evaluate the quality of a single generated image. As this annotation is too coarse as a supervision signal, we introduce two techniques: 1) a pixel-wise scheme to refine the coarse labels, and 2) multiple binary classifiers to replace a na"ive regressor. RISA is highly consistent with human preference and transfers well across models.
  arXiv  Detail & Related papers  (2021-12-08T08:22:14Z)
• Meta Internal Learning [88.68276505511922]
  Internal learning for single-image generation is a framework, where a generator is trained to produce novel images based on a single image. We propose a meta-learning approach that enables training over a collection of images, in order to model the internal statistics of the sample image more effectively. Our results show that the models obtained are as suitable as single-image GANs for many common image applications.
  arXiv  Detail & Related papers  (2021-10-06T16:27:38Z)
• Detection and Captioning with Unseen Object Classes [12.894104422808242]
  Test images may contain visual objects with no corresponding visual or textual training examples. We propose a detection-driven approach based on a generalized zero-shot detection model and a template-based sentence generation model. Our experiments show that the proposed zero-shot detection model obtains state-of-the-art performance on the MS-COCO dataset.
  arXiv  Detail & Related papers  (2021-08-13T10:43:20Z)
• Improving Generation and Evaluation of Visual Stories via Semantic Consistency [72.00815192668193]
  Given a series of natural language captions, an agent must generate a sequence of images that correspond to the captions. Prior work has introduced recurrent generative models which outperform synthesis text-to-image models on this task. We present a number of improvements to prior modeling approaches, including the addition of a dual learning framework.
  arXiv  Detail & Related papers  (2021-05-20T20:42:42Z)
• Ensembling with Deep Generative Views [72.70801582346344]
  generative models can synthesize "views" of artificial images that mimic real-world variations, such as changes in color or pose. Here, we investigate whether such views can be applied to real images to benefit downstream analysis tasks such as image classification. We use StyleGAN2 as the source of generative augmentations and investigate this setup on classification tasks involving facial attributes, cat faces, and cars.
  arXiv  Detail & Related papers  (2021-04-29T17:58:35Z)
• IMAGINE: Image Synthesis by Image-Guided Model Inversion [79.4691654458141]
  We introduce an inversion based method, denoted as IMAge-Guided model INvErsion (IMAGINE), to generate high-quality and diverse images. We leverage the knowledge of image semantics from a pre-trained classifier to achieve plausible generations. IMAGINE enables the synthesis procedure to simultaneously 1) enforce semantic specificity constraints during the synthesis, 2) produce realistic images without generator training, and 3) give users intuitive control over the generation process.
  arXiv  Detail & Related papers  (2021-04-13T02:00:24Z)
• Just Noticeable Difference for Machine Perception and Generation of Regularized Adversarial Images with Minimal Perturbation [8.920717493647121]
  We introduce a measure for machine perception inspired by the concept of Just Noticeable Difference (JND) of human perception. We suggest an adversarial image generation algorithm, which iteratively distorts an image by an additive noise until the machine learning model detects the change in the image by outputting a false label. We evaluate the adversarial images generated by our algorithm both qualitatively and quantitatively on CIFAR10, ImageNet, and MS COCO datasets.
  arXiv  Detail & Related papers  (2021-02-16T11:01:55Z)
• MirrorNet: A Deep Bayesian Approach to Reflective 2D Pose Estimation from Human Images [42.27703025887059]
  The main problems with the standard supervised approach are that it often yields anatomically implausible poses. We propose a semi-supervised method that can make effective use of images with and without pose annotations. The results of experiments show that the proposed reflective architecture makes estimated poses anatomically plausible.
  arXiv  Detail & Related papers  (2020-04-08T05:02:48Z)
• Object-Centric Image Generation from Layouts [93.10217725729468]
  We develop a layout-to-image-generation method to generate complex scenes with multiple objects. Our method learns representations of the spatial relationships between objects in the scene, which lead to our model's improved layout-fidelity. We introduce SceneFID, an object-centric adaptation of the popular Fr'echet Inception Distance metric, that is better suited for multi-object images.
  arXiv  Detail & Related papers  (2020-03-16T21:40:09Z)

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.