Object-Contextual Representations for Semantic Segmentation

In this paper, we address the semantic segmentation problem with a focus on the context aggregation strategy. Our motivation is that the label of a pixel is the category of the object that the pixel belongs to... (read more)

PDF Abstract ECCV 2020 PDF ECCV 2020 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Semantic Segmentation ADE20K val HRNetV2 + OCR + RMI (PaddleClas pretrained) mIoU 47.98 # 4
Semantic Segmentation ADE20K val OCR (ResNet-101) mIoU 45.28 # 14
Semantic Segmentation ADE20K val OCR (HRNetV2-W48) mIoU 45.66 # 13
Semantic Segmentation Cityscapes test OCR (ResNet-101, coarse) Mean IoU (class) 82.4% # 18
Semantic Segmentation Cityscapes test HRNetV2 + OCR (w/ ASP) Mean IoU (class) 83.7% # 5
Semantic Segmentation Cityscapes test HRNetV2 + OCR + Mean IoU (class) 84.5% # 2
Semantic Segmentation Cityscapes test OCR (ResNet-101) Mean IoU (class) 81.8% # 27
Semantic Segmentation Cityscapes test OCR (HRNetV2-W48, coarse) Mean IoU (class) 83.0% # 11
Semantic Segmentation Cityscapes val HRNetV2 + OCR + RMI (PaddleClas pretrained) mIoU 83.2% # 1
Semantic Segmentation Cityscapes val OCR (ResNet-101-FCN) mIoU 80.6% # 7
Semantic Segmentation COCO-Stuff test HRNetV2 + OCR + RMI (PaddleClas pretrained) mIoU 45.2% # 2
Semantic Segmentation COCO-Stuff test OCR (HRNetV2-W48) mIoU 40.5% # 5
Semantic Segmentation COCO-Stuff test OCR (ResNet-101) mIoU 39.5% # 8
Semantic Segmentation LIP val OCR (ResNet-101) mIoU 55.6% # 5
Semantic Segmentation LIP val HRNetV2 + OCR + RMI (PaddleClas pretrained) mIoU 58.2% # 2
Semantic Segmentation LIP val OCR (HRNetV2-W48) mIoU 56.65% # 3
Semantic Segmentation PASCAL Context OCR (ResNet-101) mIoU 54.8 # 14
Semantic Segmentation PASCAL Context OCR (HRNetV2-W48) mIoU 56.2 # 8
Semantic Segmentation PASCAL Context HRNetV2 + OCR + RMI (PaddleClas pretrained) mIoU 59.6 # 4
Semantic Segmentation PASCAL VOC 2012 test OCR (HRNetV2-W48) Mean IoU 84.5% # 17
Semantic Segmentation PASCAL VOC 2012 test OCR (ResNet-101) Mean IoU 84.3% # 18

Methods used in the Paper


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