Vortex Pooling: Improving Context Representation in Semantic Segmentation

Abstract

Semantic segmentation is a fundamental task in computer vision, which can be considered as a per-pixel classification problem. Recently, although fully convolutional neural network (FCN) based approaches have made remarkable progress in such task, aggregating local and contextual information in convolutional feature maps is still a challenging problem. In this paper, we argue that, when predicting the category of a given pixel, the regions close to the target are more important than those far from it. To tackle this problem, we then propose an effective yet efficient approach named Vortex Pooling to effectively utilize contextual information. Empirical studies are also provided to validate the effectiveness of the proposed method. To be specific, our approach outperforms the previous state-of-the-art model named DeepLab v3 by 1.5% on the PASCAL VOC 2012 val set and 0.6% on the test set by replacing the Atrous Spatial Pyramid Pooling (ASPP) module in DeepLab v3 with the proposed Vortex Pooling. Moreover, our model (10.13FPS) shares similar computation cost with DeepLab v3 (10.37 FPS).

References in corpus (7)

• Rethinking Atrous Convolution for Semantic Image Segmentation
• ParseNet: Looking Wider to See Better
• Learning to Segment Object Candidates
• Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
• Dilated Residual Networks
• Understanding Convolution for Semantic Segmentation
• Mixed context networks for semantic segmentation

Cited by in corpus (5)

• A Survey on Deep Learning Techniques for Stereo-based Depth Estimation
• LTC-SUM: Lightweight Client-driven Personalized Video Summarization Framework Using 2D CNN
• Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes
• Matching-space Stereo Networks for Cross-domain Generalization
• On the Synergies between Machine Learning and Binocular Stereo for Depth Estimation from Images: a Survey