Multi-scale stacked sequential learning

Sequential learning is the discipline of machine learning that deals with dependent data such that neighboring labels exhibit some kind of relationship. The paper main contribution is two-fold: first, we generalize the stacked sequential learning, highlighting the key role of neighboring interactions modeling. Second, we propose an effective and efficient way of capturing and exploiting sequential correlations that takes into account long-range interactions. We tested the method on two tasks: text lines classification and image pixel classification. Results on these tasks clearly show that our approach outperforms the standard stacked sequential learning as well as state-of-the-art conditional random fields.

► We generalized the stacked sequential learning (SSL) meta-classifier.
► We highlighted the key role of the neighboring interaction modeling in SSL.
► We propose an effective way for capturing sequential correlations.
► The algorithm outperforms both SSL and CRF on two data sets.