GFF: Gated Fully Fusion for Semantic Segmentation

TL;DR

This paper introduces Gated Fully Fusion (GFF), a novel architecture for semantic segmentation that selectively fuses multi-level features using gating mechanisms, leading to state-of-the-art results on multiple datasets.

Contribution

The paper proposes GFF, a new feature fusion method with gating to improve semantic segmentation by effectively combining multi-level features.

Findings

Achieved state-of-the-art results on Cityscapes, Pascal Context, COCO-stuff, and ADE20K datasets.

Effectively reduces noise during feature fusion with gating mechanisms.

Enhances small and thin object segmentation accuracy.

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.