Structured Prediction with Output Embeddings for Semantic Image Annotation

Ariadna Quattoni, Arnau Ramisa, Pranava Swaroop Madhyastha, Edgar Simo-Serra, Francesc Moreno-Noguer
2016 Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
We address the task of annotating images with semantic tuples. Solving this problem requires an algorithm which is able to deal with hundreds of classes for each argument of the tuple. In such contexts, data sparsity becomes a key challenge, as there will be a large number of classes for which only a few examples are available. We propose handling this by incorporating feature representations of both the inputs (images) and outputs (argument classes) into a factorized log-linear model, and
more » ... iting the flexibility of scoring functions based on bilinear forms. Experiments show that integrating feature representations of the outputs in the structured prediction model leads to better overall predictions. We also conclude that the best output representation is specific for each type of argument.
doi:10.18653/v1/n16-1068 dblp:conf/naacl/QuattoniRMSM16 fatcat:5f2k23rpbjd3ne3b2qih4eabmy