Region-Guided Pixel-Level Label Generation for Weakly Supervised Semantic Segmentation

The lack of reliable segmentation labels is the major obstacles to weakly supervised semantic segmentation. We provide a pseudo-label generation approach based on a deep convolutional neural network, which is supervised by the image-level category labels only. However, the limitation of the region of interest in the targets influences the effectiveness and integrity of the traditional methods in obtaining pixel-level mask annotations. This paper studies the characteristics of class activation mapping in classification network, focusing on the methods to enhance the localization ability of class activation mapping. We propose a Region-guided Pixel-label Generation framework (RPG) for semantic segmentation. The proposed region guidance mechanism decreases the influence of category supervision and makes use of the known high-level semantic information to guide the network, attaining more complete pixel-level annotations via expanding the regions of interest. Experimental results of training and validation on the PASCALVOC 2012 data set prove to achieve better pixel labeling and segmentation accuracy comparing with state-of-the-art methods.

[1]  Anton van den Hengel,et al.  Wider or Deeper: Revisiting the ResNet Model for Visual Recognition , 2016, Pattern Recognit..

[2]  George Papandreou,et al.  Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation , 2015, ArXiv.

[3]  Jian Sun,et al.  BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[4]  Wataru Shimoda,et al.  Distinct Class-Specific Saliency Maps for Weakly Supervised Semantic Segmentation , 2016, ECCV.

[5]  Wenyu Liu,et al.  Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  Huimin Ma,et al.  Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Jian Sun,et al.  ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Seunghoon Hong,et al.  Weakly Supervised Semantic Segmentation Using Superpixel Pooling Network , 2017, AAAI.

[10]  Seunghoon Hong,et al.  Weakly Supervised Semantic Segmentation Using Web-Crawled Videos , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Ronan Collobert,et al.  From image-level to pixel-level labeling with Convolutional Networks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Ivan Laptev,et al.  Weakly supervised object recognition with convolutional neural networks , 2014 .

[13]  Yi Yang,et al.  Self-produced Guidance for Weakly-supervised Object Localization , 2018, ECCV.

[14]  Christoph H. Lampert,et al.  Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation , 2016, ECCV.

[15]  Ivan Laptev,et al.  Is object localization for free? - Weakly-supervised learning with convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).