DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First, we highlight convolution with upsampled filters, or ’atrous convolution’, as a powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly control the resolution at which feature responses are computed within Deep Convolutional Neural Networks. It also allows us to effectively enlarge the field of view of filters to incorporate larger context without increasing the number of parameters or the amount of computation. Second, we propose atrous spatial pyramid pooling (ASPP) to robustly segment objects at multiple scales. ASPP probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multiple scales. Third, we improve the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. The commonly deployed combination of max-pooling and downsampling in DCNNs achieves invariance but has a toll on localization accuracy. We overcome this by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF), which is shown both qualitatively and quantitatively to improve localization performance. Our proposed ”DeepLab” system sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 79.7% mIOU in the test set, and advances the results on three other datasets: PASCAL-Context, PASCAL-Person-Part, and Cityscapes. All of our code is made publicly available online.

References in zbMATH (referenced in 39 articles , 1 standard article )

Showing results 1 to 20 of 39.
Sorted by year (citations)

1 2 next

  1. Lindeberg, Tony: Scale-covariant and scale-invariant Gaussian derivative networks (2022)
  2. Yu, Litao; Li, Zhibin; Xu, Min; Gao, Yongsheng; Luo, Jiebo; Zhang, Jian: Distribution-aware margin calibration for semantic segmentation in images (2022)
  3. Babu, G. Jogesh; Banks, David; Cho, Hyunsoon; Han, David; Sang, Hailin; Wang, Shouyi: A statistician teaches deep learning (2021)
  4. Chen, Zhe; Zhang, Jing; Tao, Dacheng: Recursive context routing for object detection (2021)
  5. Guo, Ruchi; Jiang, Jiahua: Construct deep neural networks based on direct sampling methods for solving electrical impedance tomography (2021)
  6. Jia, Fan; Liu, Jun; Tai, Xue-Cheng: A regularized convolutional neural network for semantic image segmentation (2021)
  7. Jin, Dequan; Qin, Ziyan; Yang, Murong; Chen, Penghe: A novel neural model with lateral interaction for learning tasks (2021)
  8. Khatri, Rajendra K. C.; Caseria, Brendan J.; Lou, Yifei; Xiao, Guanghua; Cao, Yan: Automatic extraction of cell nuclei using dilated convolutional network (2021)
  9. Mark Weber, Huiyu Wang, Siyuan Qiao, Jun Xie, Maxwell D. Collins, Yukun Zhu, Liangzhe Yuan, Dahun Kim, Qihang Yu, Daniel Cremers, Laura Leal-Taixe, Alan L. Yuille, Florian Schroff, Hartwig Adam, Liang-Chieh Chen: DeepLab2: A TensorFlow Library for Deep Labeling (2021) arXiv
  10. Nie, Yan; Zhang, Taiping; Zhao, Linchang; Ma, Xindi; Tang, Yuanyan; Liu, Xiaoyu: Siamese pyramid residual module with local binary convolution network for single object tracking (2021)
  11. Wang, Zhengyang; Ji, Shuiwang: Smoothed dilated convolutions for improved dense prediction (2021)
  12. Yang, Xu; Liu, Zhi-Yong: A doubly graduated method for inference in Markov random field (2021)
  13. Yuan, Yuhui; Huang, Lang; Guo, Jianyuan; Zhang, Chao; Chen, Xilin; Wang, Jingdong: OCNet: object context for semantic segmentation (2021)
  14. Berman, Maxim; Blaschko, Matthew B.: Discriminative training of conditional random fields with probably submodular constraints (2020)
  15. Chen, Yi-Wen; Tsai, Yi-Hsuan; Lin, Yen-Yu; Yang, Ming-Hsuan: VOSTR: video object segmentation via transferable representations (2020)
  16. Hackel, Timo; Usvyatsov, Mikhail; Galliani, Silvano; Wegner, Jan D.; Schindler, Konrad: Inference, learning and attention mechanisms that exploit and preserve sparsity in CNNs (2020)
  17. Herty, Michael; Pareschi, Lorenzo; Visconti, Giuseppe: Mean field models for large data-clustering problems (2020)
  18. Kalsi, Jaspreet Singh; Azam, Muhammad; Bouguila, Nizar: Color image segmentation using semi-bounded finite mixture models by incorporating mean templates (2020)
  19. Lindeberg, Tony: Provably scale-covariant continuous hierarchical networks based on scale-normalized differential expressions coupled in cascade (2020)
  20. Liu, Li; Ouyang, Wanli; Wang, Xiaogang; Fieguth, Paul; Chen, Jie; Liu, Xinwang; Pietikäinen, Matti: Deep learning for generic object detection: a survey (2020)

1 2 next