Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Semantic Correlation Promoted Shape-Variant Context for Segmentation

About

Context is essential for semantic segmentation. Due to the diverse shapes of objects and their complex layout in various scene images, the spatial scales and shapes of contexts for different objects have very large variation. It is thus ineffective or inefficient to aggregate various context information from a predefined fixed region. In this work, we propose to generate a scale- and shape-variant semantic mask for each pixel to confine its contextual region. To this end, we first propose a novel paired convolution to infer the semantic correlation of the pair and based on that to generate a shape mask. Using the inferred spatial scope of the contextual region, we propose a shape-variant convolution, of which the receptive field is controlled by the shape mask that varies with the appearance of input. In this way, the proposed network aggregates the context information of a pixel from its semantic-correlated region instead of a predefined fixed region. Furthermore, this work also proposes a labeling denoising model to reduce wrong predictions caused by the noisy low-level features. Without bells and whistles, the proposed segmentation network achieves new state-of-the-arts consistently on the six public segmentation datasets.

Henghui Ding, Xudong Jiang, Bing Shuai, Ai Qun Liu, Gang Wang• 2019

Related benchmarks

TaskDatasetResultRank
Semantic segmentationCityscapes (test)
mIoU81
1145
Semantic segmentationCamVid (test)
mIoU75.4
411
Semantic segmentationPASCAL Context (val)
mIoU53.2
323
Semantic segmentationCOCO Stuff
mIoU39.6
195
Semantic segmentationCoco-Stuff (test)
mIoU39.6
184
Semantic segmentationPascal Context (test)
mIoU56.2
176
Semantic segmentationPascal Context
mIoU53.2
111
Semantic segmentationPASCAL-Context 59 classes (test)
mIoU53.2
75
Semantic segmentationSIFT Flow (test)
Mean Accuracy58.2
73
Semantic segmentationPASCAL-Context 60 classes (test)
mIoU53.2
54
Showing 10 of 16 rows

Other info

Follow for update