Existing methods mostly combine the computational layer and the related losses into GCN for exploring the global graph(measuring graph structure from all data samples) or local graph (measuring graph structure from local data samples).
Most existing methods try to model the similarity relationship of the samples in the intra tasks, and generalize the model to identify the new categories.
By solving this function, we can simultaneously obtain the fusion spectral embedding from the multi-view data and the fusion structure as adjacent matrix to input graph convolutional networks for semi-supervised classification.
Ranked #28 on Node Classification on Citeseer
To address these issues, we propose a multi-stream bottom-top-bottom fully convolutional network (BTBNet), which is the first attempt to develop an end-to-end deep network for DBD.
Ranked #2 on Defocus Estimation on CUHK - Blur Detection Dataset (MAE metric)
CLA can not only build a uniform framework for adapting to multi-semantic embedding spaces, but also construct the encoder-decoder mechanism for constraining the bidirectional projection between the feature space and the class label space.
It is difficult to capture the relationship among image classes due to unseen classes, so that the manifold structure of image classes often is ignored in ZSL.