ExFuse: Enhancing Feature Fusion for Semantic Segmentation

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 ECCV 2018 PDF ECCV 2018 Abstract
No code implementations yet. Submit your code now

Results from the Paper


Ranked #3 on 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
RESULT BENCHMARK
Semantic Segmentation PASCAL VOC 2012 test ExFuse (ResNeXt-131) Mean IoU 87.9% # 6
Semantic Segmentation PASCAL VOC 2012 val ExFuse (ResNeXt-131) mIoU 85.8% # 3

Methods used in the Paper


METHOD TYPE
Average Pooling
Pooling Operations
ResNeXt Block
Skip Connection Blocks
Grouped Convolution
Convolutions
Global Average Pooling
Pooling Operations
Residual Connection
Skip Connections
ReLU
Activation Functions
Kaiming Initialization
Initialization
1x1 Convolution
Convolutions
Convolution
Convolutions
Batch Normalization
Normalization
ResNeXt
Convolutional Neural Networks