GFF: Gated Fully Fusion for Semantic Segmentation

Abstract

Semantic segmentation generates comprehensive understanding of scenes through densely predicting the category for each pixel. High-level features from Deep Convolutional Neural Networks already demonstrate their effectiveness in semantic segmentation tasks, however the coarse resolution of high-level features often leads to inferior results for small/thin objects where detailed information is important. It is natural to consider importing low level features to compensate for the lost detailed information in high-level features.Unfortunately, simply combining multi-level features suffers from the semantic gap among them. In this paper, we propose a new architecture, named Gated Fully Fusion (GFF), to selectively fuse features from multiple levels using gates in a fully connected way. Specifically, features at each level are enhanced by higher-level features with stronger semantics and lower-level features with more details, and gates are used to control the propagation of useful information which significantly reduces the noises during fusion. We achieve the state of the art results on four challenging scene parsing datasets including Cityscapes, Pascal Context, COCO-stuff and ADE20K.

accepted by AAAI-2020(oral)

References in corpus (14)

• Rethinking Atrous Convolution for Semantic Image Segmentation
• Wide Residual Networks
• Training Very Deep Networks
• ParseNet: Looking Wider to See Better
• OCNet: Object Context Network for Scene Parsing
• CCNet: Criss-Cross Attention for Semantic Segmentation
• Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
• Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
• Dual Attention Network for Scene Segmentation
• Semantic Understanding of Scenes through the ADE20K Dataset
• Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
• Expectation-Maximization Attention Networks for Semantic Segmentation
• Asymmetric Non-local Neural Networks for Semantic Segmentation
• Semantic Correlation Promoted Shape-Variant Context for Segmentation

Cited by in corpus (7)

• Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
• RFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation
• Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
• Deep Co-supervision and Attention Fusion Strategy for Automatic COVID-19 Lung Infection Segmentation on CT Images
• Global Aggregation then Local Distribution for Scene Parsing
• DFPENet-geology: A Deep Learning Framework for High Precision Recognition and Segmentation of Co-seismic Landslides
• Spatial--spectral FFPNet: Attention-Based Pyramid Network for Segmentation and Classification of Remote Sensing Images