Rethinking and Improving the Robustness of Image Style Transfer

• URL: http://arxiv.org/abs/2104.05623v1
• Date: Thu, 8 Apr 2021 03:24:45 GMT
• Title: Rethinking and Improving the Robustness of Image Style Transfer
• Authors: Pei Wang, Yijun Li, Nuno Vasconcelos
• Abstract summary: We show that the correlation between features extracted by a pre-trained VGG network has a remarkable ability to capture the visual style of an image. This quality is not robust and often degrades significantly when applied to features from more advanced and lightweight networks. We propose a solution based on a softmax transformation of the feature activations that enhances their entropy.
• Score: 70.86976598145111
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Extensive research in neural style transfer methods has shown that the correlation between features extracted by a pre-trained VGG network has a remarkable ability to capture the visual style of an image. Surprisingly, however, this stylization quality is not robust and often degrades significantly when applied to features from more advanced and lightweight networks, such as those in the ResNet family. By performing extensive experiments with different network architectures, we find that residual connections, which represent the main architectural difference between VGG and ResNet, produce feature maps of small entropy, which are not suitable for style transfer. To improve the robustness of the ResNet architecture, we then propose a simple yet effective solution based on a softmax transformation of the feature activations that enhances their entropy. Experimental results demonstrate that this small magic can greatly improve the quality of stylization results, even for networks with random weights. This suggests that the architecture used for feature extraction is more important than the use of learned weights for the task of style transfer.

Related papers

• Adaptive Convolutional Neural Network for Image Super-resolution [43.06377001247278]
  We propose a adaptive convolutional neural network for image super-resolution (ADSRNet) The upper network can enhance relation of context information, salient information relation of a kernel mapping and relations of shallow and deep layers. The lower network utilizes a symmetric architecture to enhance relations of different layers to mine more structural information.
  arXiv  Detail & Related papers  (2024-02-24T03:44:06Z)
• Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective [64.04617968947697]
  We introduce a novel data-model co-design perspective: to promote superior weight sparsity. Specifically, customized Visual Prompts are mounted to upgrade neural Network sparsification in our proposed VPNs framework.
  arXiv  Detail & Related papers  (2023-12-03T13:50:24Z)
• Power-Enhanced Residual Network for Function Approximation and Physics-Informed Inverse Problems [0.0]
  This paper introduces a novel neural network structure called the Power-Enhancing residual network. It improves the network's capabilities for both smooth and non-smooth functions approximation in 2D and 3D settings. Results emphasize the exceptional accuracy of the proposed Power-Enhancing residual network, particularly for non-smooth functions.
  arXiv  Detail & Related papers  (2023-10-24T10:01:15Z)
• 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)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• DeepRLS: A Recurrent Network Architecture with Least Squares Implicit Layers for Non-blind Image Deconvolution [15.986942312624]
  We study the problem of non-blind image deconvolution. We propose a novel recurrent network architecture that leads to very competitive restoration results of high image quality.
  arXiv  Detail & Related papers  (2021-12-10T13:16:51Z)
• SIRe-Networks: Skip Connections over Interlaced Multi-Task Learning and Residual Connections for Structure Preserving Object Classification [28.02302915971059]
  In this paper, we introduce an interlaced multi-task learning strategy, defined SIRe, to reduce the vanishing gradient in relation to the object classification task. The presented methodology directly improves a convolutional neural network (CNN) by enforcing the input image structure preservation through auto-encoders. To validate the presented methodology, a simple CNN and various implementations of famous networks are extended via the SIRe strategy and extensively tested on the CIFAR100 dataset.
  arXiv  Detail & Related papers  (2021-10-06T13:54:49Z)
• Evolving Architectures with Gradient Misalignment toward Low Adversarial Transferability [4.415977307120616]
  We propose an architecture searching framework that employs neuroevolution to evolve network architectures. Our experiments show that the proposed framework successfully discovers architectures that reduce transferability from four standard networks. In addition, the evolved networks trained with gradient misalignment exhibit significantly lower transferability compared to standard networks trained with gradient misalignment.
  arXiv  Detail & Related papers  (2021-09-13T12:41:53Z)
• Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition [77.95361323613147]
  Current state-of-the-art visual recognition systems rely on pretraining a neural network on a large-scale dataset and finetuning the network weights on a smaller dataset. In this work, we prove that dynamically adapting network architectures tailored for each domain task along with weight finetuning benefits in both efficiency and effectiveness. Our method can be easily generalized to an unsupervised paradigm by replacing supernet training with self-supervised learning in the source domain tasks and performing linear evaluation in the downstream tasks.
  arXiv  Detail & Related papers  (2021-03-31T08:15:17Z)
• Towards Analysis-friendly Face Representation with Scalable Feature and Texture Compression [113.30411004622508]
  We show that a universal and collaborative visual information representation can be achieved in a hierarchical way. Based on the strong generative capability of deep neural networks, the gap between the base feature layer and enhancement layer is further filled with the feature level texture reconstruction. To improve the efficiency of the proposed framework, the base layer neural network is trained in a multi-task manner.
  arXiv  Detail & Related papers  (2020-04-21T14:32:49Z)

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.