Pixel Level Data Augmentation for Semantic Image Segmentation Using Generative Adversarial Networks

@article{Liu2019PixelLD,
  title={Pixel Level Data Augmentation for Semantic Image Segmentation Using Generative Adversarial Networks},
  author={Shuangting Liu and Jiaqi Zhang and Yuxin Chen and Yifan Liu and Zengchang Qin and Tao Wan},
  journal={ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2019},
  pages={1902-1906}
}
  • Shuangting Liu, Jiaqi Zhang, +3 authors T. Wan
  • Published 1 November 2018
  • Computer Science
  • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Semantic segmentation is one of the basic topics in computer vision, it aims to assign semantic labels to every pixel of an image. Unbalanced semantic label distribution could have a negative influence on segmentation accuracy. In this paper, we investigate using data augmentation approach to balance the semantic label distribution in order to improve segmentation performance. We propose using generative adversarial networks (GANs) to generate realistic images for improving the performance of… 
Attention-Based Network for Semantic Image Segmentation via Adversarial Learning
TLDR
This paper explores the attention mechanism for semantic segmentation to improve the extraction and recovery of information efficiently and shows the performance is further advanced with the addition of adversarial learning.
Stable self-attention adversarial learning for semi-supervised semantic image segmentation
TLDR
This work addresses the issue of adversarial learning for semi-supervised semantic image segmentation by introducing a self-attention mechanism in the generator of the GAN to effectively account for relationships between widely separated spatial regions of the input image with supervision based on pixel-level ground truth data.
Improved Image Semantic Segmentation Based on Cascade Data Augmentation
A large portion of the research for the task of image semantic segmentation focuses on optimizing deep learning networks to improve the state-of-the-art results. In this work, however, we take a
Recognizing novel patterns via adversarial learning for one-shot semantic segmentation
TLDR
This study proposes a procedure based on the generative adversarial network to enable the one-shot semantic segmentation model for learning information from previously unknown categories, and contains a segmentation network that generates segmentation predictions.
Self-Ensembling With GAN-Based Data Augmentation for Domain Adaptation in Semantic Segmentation
TLDR
A self-ensembling technique based on Generative Adversarial Networks, which is computationally efficient and effective to facilitate domain alignment and outperforms state-of-the-art semantic segmentation methods on unsupervised domain adaptation benchmarks.
Improving Semantic Segmentation via Video Propagation and Label Relaxation
TLDR
This paper presents a video prediction-based methodology to scale up training sets by synthesizing new training samples in order to improve the accuracy of semantic segmentation networks, and introduces a novel boundary label relaxation technique that makes training robust to annotation noise and propagation artifacts along object boundaries.
Data Selection for training Semantic Segmentation CNNs with cross-dataset weak supervision
TLDR
Two methods for selecting the most relevant data with weak supervision are proposed for finding visually similar images without the need of labels and is based on modeling image representations with a Gaussian Mixture Model (GMM).
Semanticgan: Generative Adversarial Networks For Semantic Image To Photo-Realistic Image Translation
TLDR
A SemanticGAN to synthesize high resolution image with fine details and realistic textures from the semantic label map and a Semantic Information Preserved Loss (SIPL) to maintain semantic information in the process of the generation via a segmentation model are proposed.
Data augmentation using image-to-image translation for detecting forest strip roads based on deep learning
  • Kengo Usui
  • Computer Science
    International Journal of Forest Engineering
  • 2020
TLDR
Three GAN-based data augmentation methods are proposed, namely, translated images from new label images, translations from an actual dataset, and both, which are effective for detecting a small number class because the class distribution of the dataset is set arbitrarily.
Microscopic Image Augmentation Using an Enhanced WGAN
TLDR
An Enhanced E-WGAN that combines geometric transformation methods and Wasserstein Generative Adversarial Networks (WGAN) for EM image augmentation and performs color space augmentation to the original EM images is proposed.
...
1
2
3
4
...

References

SHOWING 1-10 OF 23 REFERENCES
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
TLDR
A new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs) is presented, which significantly outperforms existing methods, advancing both the quality and the resolution of deep image synthesis and editing.
Image-to-Image Translation with Conditional Adversarial Networks
TLDR
Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.
Rethinking Atrous Convolution for Semantic Image Segmentation
TLDR
The proposed `DeepLabv3' system significantly improves over the previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.
Emotion Classification with Data Augmentation Using Generative Adversarial Networks
TLDR
This paper designs a framework using a CNN model as the classifier and a cycle-consistent adversarial networks (CycleGAN) as the generator, and employs the least-squared loss as adversarial loss to avoid gradient vanishing problem.
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
TLDR
This work addresses the task of semantic image segmentation with Deep Learning and proposes atrous spatial pyramid pooling (ASPP), which is proposed to robustly segment objects at multiple scales, and improves the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models.
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
TLDR
This work extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries and applies the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network.
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
  • C. Ledig, Lucas Theis, +6 authors W. Shi
  • Computer Science, Mathematics
    2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
TLDR
SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss.
Pyramid Scene Parsing Network
TLDR
This paper exploits the capability of global context information by different-region-based context aggregation through the pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet) to produce good quality results on the scene parsing task.
Improving person detection using synthetic training data
Person detection in complex real-world scenes is a challenging problem. State-of-the-art methods typically use supervised learning relying on significant amounts of training data to achieve good
Photographic Image Synthesis with Cascaded Refinement Networks
  • Qifeng Chen, V. Koltun
  • Computer Science
    2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
TLDR
It is shown that photographic images can be synthesized from semantic layouts by a single feedforward network with appropriate structure, trained end-to-end with a direct regression objective.
...
1
2
3
...