Effective Shortcut Technique for GAN

• URL: http://arxiv.org/abs/2201.11351v1
• Date: Thu, 27 Jan 2022 07:14:45 GMT
• Title: Effective Shortcut Technique for GAN
• Authors: Seung Park, Cheol-Hwan Yoo, Yong-Goo Shin
• Abstract summary: generative adversarial network (GAN)-based image generation techniques design their generators by stacking up multiple residual blocks. The residual block generally contains a shortcut, ie skip connection, which effectively supports information propagation in the network. We propose a novel shortcut method, called the gated shortcut, which not only embraces the strength point of the residual block but also further boosts the GAN performance.
• Score: 6.007303976935779
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, generative adversarial network (GAN)-based image generation techniques design their generators by stacking up multiple residual blocks. The residual block generally contains a shortcut, \ie skip connection, which effectively supports information propagation in the network. In this paper, we propose a novel shortcut method, called the gated shortcut, which not only embraces the strength point of the residual block but also further boosts the GAN performance. More specifically, based on the gating mechanism, the proposed method leads the residual block to keep (or remove) information that is relevant (or irrelevant) to the image being generated. To demonstrate that the proposed method brings significant improvements in the GAN performance, this paper provides extensive experimental results on the various standard datasets such as CIFAR-10, CIFAR-100, LSUN, and tiny-ImageNet. Quantitative evaluations show that the gated shortcut achieves the impressive GAN performance in terms of Frechet inception distance (FID) and Inception score (IS). For instance, the proposed method improves the FID and IS scores on the tiny-ImageNet dataset from 35.13 to 27.90 and 20.23 to 23.42, respectively.

Related papers

• Efficient GANs for Document Image Binarization Based on DWT and Normalization [7.597556504891501]
  generative adversarial networks (GANs) can generate images where shadows and noise are effectively removed, which allow for text information extraction. This work introduces an efficient GAN method based on the three-stage network architecture that incorporates the Discrete Wavelet Transformation and normalization. Experimental results show that the proposed method reduces the training time by 10% and the inference time by 26% when compared to the SOTA method.
  arXiv  Detail & Related papers  (2024-07-05T03:19:32Z)
• Weakly Supervised LiDAR Semantic Segmentation via Scatter Image Annotation [38.715754110667916]
  We implement LiDAR semantic segmentation using scatter image annotation. We also propose ScatterNet, a network that includes three pivotal strategies to reduce the performance gap. Our method requires less than 0.02% of the labeled points to achieve over 95% of the performance of fully-supervised methods.
  arXiv  Detail & Related papers  (2024-04-19T13:01:30Z)
• Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach [58.57026686186709]
  We introduce the Convolutional Transformer layer (ConvFormer) and propose a ConvFormer-based Super-Resolution network (CFSR) CFSR inherits the advantages of both convolution-based and transformer-based approaches. Experiments demonstrate that CFSR strikes an optimal balance between computational cost and performance.
  arXiv  Detail & Related papers  (2024-01-11T03:08:00Z)
• Deep Multi-Threshold Spiking-UNet for Image Processing [51.88730892920031]
  This paper introduces the novel concept of Spiking-UNet for image processing, which combines the power of Spiking Neural Networks (SNNs) with the U-Net architecture. To achieve an efficient Spiking-UNet, we face two primary challenges: ensuring high-fidelity information propagation through the network via spikes and formulating an effective training strategy. Experimental results show that, on image segmentation and denoising, our Spiking-UNet achieves comparable performance to its non-spiking counterpart.
  arXiv  Detail & Related papers  (2023-07-20T16:00:19Z)
• Manifold Constraint Regularization for Remote Sensing Image Generation [34.68714863219855]
  Generative Adversarial Networks (GANs) have shown notable accomplishments in remote sensing domain. This paper analyzes the characteristics of remote sensing images and proposes manifold constraint regularization.
  arXiv  Detail & Related papers  (2023-05-31T02:35:41Z)
• RDRN: Recursively Defined Residual Network for Image Super-Resolution [58.64907136562178]
  Deep convolutional neural networks (CNNs) have obtained remarkable performance in single image super-resolution. We propose a novel network architecture which utilizes attention blocks efficiently.
  arXiv  Detail & Related papers  (2022-11-17T11:06:29Z)
• A Novel Generator with Auxiliary Branch for Improving GAN Performance [7.005458308454871]
  This brief introduces a novel generator architecture that produces the image by combining features obtained through two different branches. The goal of the main branch is to produce the image by passing through the multiple residual blocks, whereas the auxiliary branch is to convey the coarse information in the earlier layer to the later one. To prove the superiority of the proposed method, this brief provides extensive experiments using various standard datasets.
  arXiv  Detail & Related papers  (2021-12-30T08:38:49Z)
• Semantic Segmentation by Improved Generative Adversarial Networks [0.0]
  We introduce Convolutional CRFs (ConvCRFs) as an effective improvement solution for the image semantic segmentation task. Our method not only learns an end-to-end mapping from input image to corresponding output image, but also learns a loss function to train this mapping.
  arXiv  Detail & Related papers  (2021-04-20T11:59:29Z)
• Manifold Regularized Dynamic Network Pruning [102.24146031250034]
  This paper proposes a new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks. The effectiveness of the proposed method is verified on several benchmarks, which shows better performance in terms of both accuracy and computational cost.
  arXiv  Detail & Related papers  (2021-03-10T03:59:03Z)
• Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection [63.18846475183332]
  We aim to develop an efficient and compact deep network for RGB-D salient object detection. We propose a progressively guided alternate refinement network to refine it. Our model outperforms existing state-of-the-art approaches by a large margin.
  arXiv  Detail & Related papers  (2020-08-17T02:55:06Z)
• Resolution Adaptive Networks for Efficient Inference [53.04907454606711]
  We propose a novel Resolution Adaptive Network (RANet), which is inspired by the intuition that low-resolution representations are sufficient for classifying "easy" inputs. In RANet, the input images are first routed to a lightweight sub-network that efficiently extracts low-resolution representations. High-resolution paths in the network maintain the capability to recognize the "hard" samples.
  arXiv  Detail & Related papers  (2020-03-16T16:54:36Z)

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.