AdaWCT: Adaptive Whitening and Coloring Style Injection

• URL: http://arxiv.org/abs/2208.00921v1
• Date: Mon, 1 Aug 2022 15:07:51 GMT
• Title: AdaWCT: Adaptive Whitening and Coloring Style Injection
• Authors: Antoine Dufour, Yohan Poirier-Ginter, Alexandre Lessard, Ryan Smith, Michael Lockyer and Jean-Francois Lalonde
• Abstract summary: We present a generalization of AdaIN which relies on the whitening and coloring transformation (WCT) which we dub AdaWCT, that we apply for style injection in large GANs. We show, through experiments on the StarGANv2 architecture, that this generalization, albeit conceptually simple, results in significant improvements in the quality of the generated images.
• Score: 55.554986498301574
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adaptive instance normalization (AdaIN) has become the standard method for style injection: by re-normalizing features through scale-and-shift operations, it has found widespread use in style transfer, image generation, and image-to-image translation. In this work, we present a generalization of AdaIN which relies on the whitening and coloring transformation (WCT) which we dub AdaWCT, that we apply for style injection in large GANs. We show, through experiments on the StarGANv2 architecture, that this generalization, albeit conceptually simple, results in significant improvements in the quality of the generated images.

Related papers

• StainFuser: Controlling Diffusion for Faster Neural Style Transfer in Multi-Gigapixel Histology Images [5.382682403111961]
  Stain normalization algorithms aim to transform the color and intensity characteristics of a source multi-gigapixel histology image to match those of a target image. We propose a new approach, StainFuser, which treats this problem as a style transfer task using a novel Conditional Latent Diffusion architecture.
  arXiv  Detail & Related papers  (2024-03-14T11:49:43Z)
• 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)
• Condition-Invariant Semantic Segmentation [77.10045325743644]
  We implement Condition-Invariant Semantic (CISS) on the current state-of-the-art domain adaptation architecture. Our method achieves the second-best performance on the normal-to-adverse Cityscapes$to$ACDC benchmark. CISS is shown to generalize well to domains unseen during training, such as BDD100K-night and ACDC-night.
  arXiv  Detail & Related papers  (2023-05-27T03:05:07Z)
• Spectral Normalization and Dual Contrastive Regularization for Image-to-Image Translation [9.029227024451506]
  We propose a new unpaired I2I translation framework based on dual contrastive regularization and spectral normalization. We conduct comprehensive experiments to evaluate the effectiveness of SN-DCR, and the results prove that our method achieves SOTA in multiple tasks.
  arXiv  Detail & Related papers  (2023-04-22T05:22:24Z)
• Masked and Adaptive Transformer for Exemplar Based Image Translation [16.93344592811513]
  Cross-domain semantic matching is challenging. We propose a masked and adaptive transformer (MAT) for learning accurate cross-domain correspondence. We devise a novel contrastive style learning method, for acquire quality-discriminative style representations.
  arXiv  Detail & Related papers  (2023-03-30T03:21:14Z)
• Ultra-high-resolution unpaired stain transformation via Kernelized Instance Normalization [1.2234742322758418]
  We propose a strategy for ultra-high-resolution unpaired image-to-image translation: Kernelized Instance Normalization (KIN) KIN preserves local information and successfully achieves seamless stain transformation with constant GPU memory usage. This is the first successful study for the ultra-high-resolution unpaired image-to-image translation with constant space complexity.
  arXiv  Detail & Related papers  (2022-08-23T04:47:43Z)
• Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis [68.1281982092765]
  We propose a novel normalization module, termed as REtrieval-based Spatially AdaptIve normaLization (RESAIL) RESAIL provides pixel level fine-grained guidance to the normalization architecture. Experiments on several challenging datasets show that our RESAIL performs favorably against state-of-the-arts in terms of quantitative metrics, visual quality, and subjective evaluation.
  arXiv  Detail & Related papers  (2022-04-06T14:21:39Z)
• Adaptive Image Transformations for Transfer-based Adversarial Attack [73.74904401540743]
  We propose a novel architecture, called Adaptive Image Transformation Learner (AITL) Our elaborately designed learner adaptively selects the most effective combination of image transformations specific to the input image. Our method significantly improves the attack success rates on both normally trained models and defense models under various settings.
  arXiv  Detail & Related papers  (2021-11-27T08:15:44Z)
• Style-invariant Cardiac Image Segmentation with Test-time Augmentation [10.234493507401618]
  Deep models often suffer from severe performance drop due to the appearance shift in the real clinical setting. In this paper, we propose a novel style-invariant method for cardiac image segmentation.
  arXiv  Detail & Related papers  (2020-09-24T08:27:40Z)
• Supervised and Unsupervised Learning of Parameterized Color Enhancement [112.88623543850224]
  We tackle the problem of color enhancement as an image translation task using both supervised and unsupervised learning. We achieve state-of-the-art results compared to both supervised (paired data) and unsupervised (unpaired data) image enhancement methods on the MIT-Adobe FiveK benchmark. We show the generalization capability of our method, by applying it on photos from the early 20th century and to dark video frames.
  arXiv  Detail & Related papers  (2019-12-30T13:57:06Z)

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.