Hierarchical zero-shot classification with convolutional neural network features and semantic attribute learning
MVA, pp. 194-197, 2017.
We examine hierarchical approaches to image classification problems that include categories for which we have no training examples. Building on prior work in hierarchical classification that optimizes the trade-off between depth in a tree and accuracy of placement, we compare the performance of multiple formulations of the problem on both...More
Full Text (Upload PDF)
PPT (Upload PPT)