ExFuse: Enhancing Feature Fusion for Semantic Segmentation

ECCV 2018 Zhenli ZhangXiangyu ZhangChao PengDazhi ChengJian Sun

Modern semantic segmentation frameworks usually combine low-level and high-level features from pre-trained backbone convolutional models to boost performance. In this paper, we first point out that a simple fusion of low-level and high-level features could be less effective because of the gap in semantic levels and spatial resolution... (read more)

PDF Abstract

Evaluation Results from the Paper


 SOTA for Semantic Segmentation on PASCAL VOC 2012 val (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
COMPARE
Semantic Segmentation PASCAL VOC 2012 test ExFuse (ResNeXt-131) Mean IoU 87.9% # 2
Semantic Segmentation PASCAL VOC 2012 val ExFuse (ResNeXt-131) mIoU 85.8% # 1