CVSep 20, 2019

ACFNet: Attentional Class Feature Network for Semantic Segmentation

arXiv:1909.09408v3299 citations
AI Analysis

This work addresses semantic segmentation for computer vision applications, offering an incremental improvement over existing methods.

The paper tackles semantic segmentation by introducing class centers to capture global context from a categorical perspective, achieving a state-of-the-art performance of 81.85% mIoU on the Cityscapes dataset.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes