Semantic Segmentation Modules

Short-Term Dense Concatenate

Introduced by Fan et al. in Rethinking BiSeNet For Real-time Semantic Segmentation

STDC, or Short-Term Dense Concatenate, is a module for semantic segmentation to extract deep features with scalable receptive field and multi-scale information. It aims to remove structure redundancy in the BiSeNet architecture, specifically BiSeNet adds an extra path to encode spatial information which can be time-consuming,. Instead, STDC gradually reduces the dimension of feature maps and use the aggregation of them for image representation.

We concatenate response maps from multiple continuous layers, each of which encodes input image/feature in different scales and respective fields, leading to multi-scale feature representation. To speed up, the filter size of layers is gradually reduced with negligible loss in segmentation performance.

Source: Rethinking BiSeNet For Real-time Semantic Segmentation


Paper Code Results Date Stars