Review -- CCNet: Criss-Cross Attention for Semantic Segmentation

In TPAMI, besides cross-entropy loss lseg for segmentation loss, there is also the category consistent loss to drive RCCA module to learn category consistent features directly. In TPAMI, besides cross-entropy loss lseg for segmentation loss, there is also the category consistent loss to drive RCCA module to learn category consistent features directly. Let C be the set of classes, Nc is the number of valid elements belonging to category c. hi is the feature vector at spatial position i. μc is the mean feature of category c C (the cluster center). To reduce the computation load, a convolutional layer with 1 1 filters is first applied on the output of RCCA module for dimension reduction and then these three losses are applied on the feature map with fewer channels. Let C be the set of classes, Nc is the number of valid elements belonging to category c. hi is the feature vector at spatial position i. μc is the mean feature of category c C (the cluster center).