Anysize GAN: A solution to the image-warping problem

• URL: http://arxiv.org/abs/2003.03233v2
• Date: Wed, 8 Jul 2020 21:19:38 GMT
• Title: Anysize GAN: A solution to the image-warping problem
• Authors: Connah Kendrick, David Gillespie, Moi Hoon Yap
• Abstract summary: We propose a new type of General Adversarial Network (GAN) to resolve a common issue with Deep Learning. We develop a novel architecture that can be applied to existing latent vector based GAN structures that allows them to generate on-the-fly images of any size. We demonstrate our method can successfully generate realistic images at different sizes without issue, preserving and understanding spatial relationships, while maintaining feature relationships.
• Score: 5.866114531330298
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a new type of General Adversarial Network (GAN) to resolve a common issue with Deep Learning. We develop a novel architecture that can be applied to existing latent vector based GAN structures that allows them to generate on-the-fly images of any size. Existing GAN for image generation requires uniform images of matching dimensions. However, publicly available datasets, such as ImageNet contain thousands of different sizes. Resizing image causes deformations and changing the image data, whereas as our network does not require this preprocessing step. We make significant changes to the standard data loading techniques to enable any size image to be loaded for training. We also modify the network in two ways, by adding multiple inputs and a novel dynamic resizing layer. Finally we make adjustments to the discriminator to work on multiple resolutions. These changes can allow multiple resolution datasets to be trained on without any resizing, if memory allows. We validate our results on the ISIC 2019 skin lesion dataset. We demonstrate our method can successfully generate realistic images at different sizes without issue, preserving and understanding spatial relationships, while maintaining feature relationships. We will release the source codes upon paper acceptance.

Related papers

• Elastic-DETR: Making Image Resolution Learnable with Content-Specific Network Prediction [0.612477318852572]
  We introduce a novel strategy for learnable resolution, called Elastic-DETR, enabling elastic utilization of multiple image resolutions. Our network provides an adaptive scale factor based on the content of the image with a compact scale prediction module. By leveraging the resolution's flexibility, we can demonstrate various models that exhibit varying trade-offs between accuracy and computational complexity.
  arXiv  Detail & Related papers  (2024-12-09T09:46:21Z)
• SCAResNet: A ResNet Variant Optimized for Tiny Object Detection in Transmission and Distribution Towers [0.42028553027796633]
  Traditional deep learning-based object detection networks often resize images during the data pre-processing stage to achieve a uniform size and scale in the feature map. We introduce Positional-Multi-head Criss-Cross Imagery to capture contextual information and learn from multiple representation subspaces. This approach allows images of different sizes and scales to generate feature maps with uniform dimensions and can be employed in feature map propagation.
  arXiv  Detail & Related papers  (2024-04-05T15:48:36Z)
• Supervised Deep Learning for Content-Aware Image Retargeting with Fourier Convolutions [11.031841470875571]
  Image aims to alter the size of the image with attention to the contents. Labeled datasets are unavailable for training deep learning models in the image tasks. Regular convolutional neural networks cannot generate images of different sizes in inference time.
  arXiv  Detail & Related papers  (2023-06-12T19:17:44Z)
• SARAS-Net: Scale and Relation Aware Siamese Network for Change Detection [6.12477318852572]
  Change detection (CD) aims to find the difference between two images at different times and outputs a change map to represent whether the region has changed or not. Many State-of-The-Art (SoTA) methods design a deep learning model that has a powerful discriminative ability. We propose our network, the Scale and Relation-Aware Siamese Network (SARAS-Net) to deal with this issue.
  arXiv  Detail & Related papers  (2022-12-02T16:30:33Z)
• Learning Enriched Features for Fast Image Restoration and Enhancement [166.17296369600774]
  This paper presents a holistic goal of maintaining spatially-precise high-resolution representations through the entire network. We learn an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details. Our approach achieves state-of-the-art results for a variety of image processing tasks, including defocus deblurring, image denoising, super-resolution, and image enhancement.
  arXiv  Detail & Related papers  (2022-04-19T17:59:45Z)
• Any-resolution Training for High-resolution Image Synthesis [55.19874755679901]
  Generative models operate at fixed resolution, even though natural images come in a variety of sizes. We argue that every pixel matters and create datasets with variable-size images, collected at their native resolutions. We introduce continuous-scale training, a process that samples patches at random scales to train a new generator with variable output resolutions.
  arXiv  Detail & Related papers  (2022-04-14T17:59:31Z)
• InvGAN: Invertible GANs [88.58338626299837]
  InvGAN, short for Invertible GAN, successfully embeds real images to the latent space of a high quality generative model. This allows us to perform image inpainting, merging, and online data augmentation.
  arXiv  Detail & Related papers  (2021-12-08T21:39:00Z)
• Multi-Domain Image-to-Image Translation with Adaptive Inference Graph [29.673550911992365]
  Current state of the art models require a large and deep model to handle the visual diversity of multiple domains. We propose to increase the network capacity by using an adaptive graph structure. This approach leads to an adjustable increase in number of parameters while preserving an almost constant computational cost.
  arXiv  Detail & Related papers  (2021-01-11T10:47:29Z)
• Memory-efficient GAN-based Domain Translation of High Resolution 3D Medical Images [0.15092198588928965]
  Generative adversarial networks (GANs) are rarely applied on 3D medical images of large size. The present work proposes a multi-scale patch-based GAN approach for establishing unpaired domain translation. The evaluation of the domain translation scenarios is performed on brain MRIs of size 155x240x240 and thorax CTs of size up to 512x512x512.
  arXiv  Detail & Related papers  (2020-10-06T08:43:27Z)
• Shape Adaptor: A Learnable Resizing Module [59.940372879848624]
  We present a novel resizing module for neural networks: shape adaptor, a drop-in enhancement built on top of traditional resizing layers. Our implementation enables shape adaptors to be trained end-to-end without any additional supervision. We show the effectiveness of shape adaptors on two other applications: network compression and transfer learning.
  arXiv  Detail & Related papers  (2020-08-03T14:15:52Z)
• Learning to Learn Parameterized Classification Networks for Scalable Input Images [76.44375136492827]
  Convolutional Neural Networks (CNNs) do not have a predictable recognition behavior with respect to the input resolution change. We employ meta learners to generate convolutional weights of main networks for various input scales. We further utilize knowledge distillation on the fly over model predictions based on different input resolutions.
  arXiv  Detail & Related papers  (2020-07-13T04:27:25Z)
• Locally Masked Convolution for Autoregressive Models [107.4635841204146]
  LMConv is a simple modification to the standard 2D convolution that allows arbitrary masks to be applied to the weights at each location in the image. We learn an ensemble of distribution estimators that share parameters but differ in generation order, achieving improved performance on whole-image density estimation.
  arXiv  Detail & Related papers  (2020-06-22T17:59:07Z)

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.