ACFNet: Attentional Class Feature Network for Semantic Segmentation
arXiv:1909.09408
Abstract
Recent works have made great progress in semantic segmentation by exploiting richer context, most of which are designed from a spatial perspective. In contrast to previous works, we present the concept of class center which extracts the global context from a categorical perspective. This class-level context describes the overall representation of each class in an image. We further propose a novel module, named Attentional Class Feature (ACF) module, to calculate and adaptively combine different class centers according to each pixel. Based on the ACF module, we introduce a coarse-to-fine segmentation network, called Attentional Class Feature Network (ACFNet), which can be composed of an ACF module and any off-the-shell segmentation network (base network). In this paper, we use two types of base networks to evaluate the effectiveness of ACFNet. We achieve new state-of-the-art performance of 81.85% mIoU on Cityscapes dataset with only finely annotated data used for training.
Accepted to ICCV 2019
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Rethinking Atrous Convolution for Semantic Image Segmentation
- ParseNet: Looking Wider to See Better
- OCNet: Object Context Network for Scene Parsing
- High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks
- Label Refinement Network for Coarse-to-Fine Semantic Segmentation
- ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors
Cited by in corpus (8)
- ABCNet: Attentive Bilateral Contextual Network for Efficient Semantic Segmentation of Fine-Resolution Remote Sensing Images
- Hierarchical Multi-Scale Attention for Semantic Segmentation
- Deep Co-supervision and Attention Fusion Strategy for Automatic COVID-19 Lung Infection Segmentation on CT Images
- PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation
- Multi-Scale Feature Aggregation by Cross-Scale Pixel-to-Region Relation Operation for Semantic Segmentation
- Hierarchical Pyramid Representations for Semantic Segmentation
- Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation
- BiCANet: Bi-directional Contextual Aggregating Network for Image Semantic Segmentation