Automatic Correction of Internal Units in Generative Neural Networks

• URL: http://arxiv.org/abs/2104.06118v1
• Date: Tue, 13 Apr 2021 11:46:45 GMT
• Title: Automatic Correction of Internal Units in Generative Neural Networks
• Authors: Ali Tousi, Haedong Jeong, Jiyeon Han, Hwanil Choi and Jaesik Choi
• Abstract summary: Generative Adversarial Networks (GANs) have shown satisfactory performance in synthetic image generation. There exists a number of generated images with defective visual patterns which are known as artifacts. In this work, we devise a method that automatically identifies the internal units generating various types of artifact images.
• Score: 15.67941936262584
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative Adversarial Networks (GANs) have shown satisfactory performance in synthetic image generation by devising complex network structure and adversarial training scheme. Even though GANs are able to synthesize realistic images, there exists a number of generated images with defective visual patterns which are known as artifacts. While most of the recent work tries to fix artifact generations by perturbing latent code, few investigate internal units of a generator to fix them. In this work, we devise a method that automatically identifies the internal units generating various types of artifact images. We further propose the sequential correction algorithm which adjusts the generation flow by modifying the detected artifact units to improve the quality of generation while preserving the original outline. Our method outperforms the baseline method in terms of FID-score and shows satisfactory results with human evaluation.

Related papers

• RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection [60.960988614701414]
  RIGID is a training-free and model-agnostic method for robust AI-generated image detection. RIGID significantly outperforms existing trainingbased and training-free detectors.
  arXiv  Detail & Related papers  (2024-05-30T14:49:54Z)
• Active Generation for Image Classification [45.93535669217115]
  We propose to address the efficiency of image generation by focusing on the specific needs and characteristics of the model. With a central tenet of active learning, our method, named ActGen, takes a training-aware approach to image generation.
  arXiv  Detail & Related papers  (2024-03-11T08:45:31Z)
• Distance Weighted Trans Network for Image Completion [52.318730994423106]
  We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components. CNNs are used to augment the local texture information of coarse priors. DWT blocks are used to recover certain coarse textures and coherent visual structures.
  arXiv  Detail & Related papers  (2023-10-11T12:46:11Z)
• Diffusion Brush: A Latent Diffusion Model-based Editing Tool for AI-generated Images [10.323260768204461]
  Text-to-image generative models have made remarkable advancements in generating high-quality images. Existing techniques to fine-tune generated images are time-consuming (manual editing), produce poorly-integrated results (inpainting), or result in unexpected changes across the entire image. We present Diffusion Brush, a Latent Diffusion Model-based (LDM) tool to efficiently fine-tune desired regions within an AI-synthesized image.
  arXiv  Detail & Related papers  (2023-05-31T22:27:21Z)
• Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs [104.72108627191041]
  We show that conventional neural network classifiers can generate high-quality images comparable to state-of-the-art generative models. We propose a mask-based reconstruction module to make semantic gradients-aware to synthesize plausible images. We show that our method is also applicable to text-to-image generation by regarding image-text foundation models.
  arXiv  Detail & Related papers  (2022-11-27T11:25:35Z)
• Self-supervised GAN Detector [10.963740942220168]
  generative models can be abused with malicious purposes, such as fraud, defamation, and fake news. We propose a novel framework to distinguish the unseen generated images outside of the training settings. Our proposed method is composed of the artificial fingerprint generator reconstructing the high-quality artificial fingerprints of GAN images.
  arXiv  Detail & Related papers  (2021-11-12T06:19:04Z)
• 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)
• MOGAN: Morphologic-structure-aware Generative Learning from a Single Image [59.59698650663925]
  Recently proposed generative models complete training based on only one image. We introduce a MOrphologic-structure-aware Generative Adversarial Network named MOGAN that produces random samples with diverse appearances. Our approach focuses on internal features including the maintenance of rational structures and variation on appearance.
  arXiv  Detail & Related papers  (2021-03-04T12:45:23Z)
• Generative Hierarchical Features from Synthesizing Images [65.66756821069124]
  We show that learning to synthesize images can bring remarkable hierarchical visual features that are generalizable across a wide range of applications. The visual feature produced by our encoder, termed as Generative Hierarchical Feature (GH-Feat), has strong transferability to both generative and discriminative tasks.
  arXiv  Detail & Related papers  (2020-07-20T18:04:14Z)
• Pixel-wise Conditioned Generative Adversarial Networks for Image Synthesis and Completion [3.8807073304999355]
  Generative Adversarial Networks (GANs) have proven successful for unsupervised image generation. We investigate the effectiveness of conditioning GANs when very few pixel values are provided. We propose a modelling framework which results in adding an explicit cost term to the GAN objective function to enforce pixel-wise conditioning.
  arXiv  Detail & Related papers  (2020-02-04T13:49:15Z)

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.