Class Guided Channel Weighting Network for Fine-Grained Semantic Segmentation

Authors

  • Xiang Zhang Northwest University of China
  • Wanqing Zhao Northwest University of China
  • Hangzai Luo Northwest University of China
  • Jinye Peng Northwest University of China
  • Jianping Fan Northwest University of China

DOI:

https://doi.org/10.1609/aaai.v36i3.20244

Keywords:

Computer Vision (CV)

Abstract

Deep learning has achieved promising performance on semantic segmentation, but few works focus on semantic segmentation at the fine-grained level. Fine-grained semantic segmentation requires recognizing and distinguishing hundreds of sub-categories. Due to the high similarity of different sub-categories and large variations in poses, scales, rotations, and color of the same sub-category in the fine-grained image set, the performance of traditional semantic segmentation methods will decline sharply. To alleviate these dilemmas, a new approach, named Class Guided Channel Weighting Network (CGCWNet), is developed in this paper to enable fine-grained semantic segmentation. For the large intra-class variations, we propose a Class Guided Weighting (CGW) module, which learns the image-level fine-grained category probabilities by exploiting second-order feature statistics, and use them as global information to guide semantic segmentation. For the high similarity between different sub-categories, we specially build a Channel Relationship Attention (CRA) module to amplify the distinction of features. Furthermore, a Detail Enhanced Guided Filter (DEGF) module is proposed to refine the boundaries of object masks by using an edge contour cue extracted from the enhanced original image. Experimental results on PASCAL VOC 2012 and six fine-grained image sets show that our proposed CGCWNet has achieved state-of-the-art results.

Downloads

Published

2022-06-28

How to Cite

Zhang, X., Zhao, W., Luo, H., Peng, J., & Fan, J. (2022). Class Guided Channel Weighting Network for Fine-Grained Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 36(3), 3344-3352. https://doi.org/10.1609/aaai.v36i3.20244

Issue

Section

AAAI Technical Track on Computer Vision III