Based on the observation that semantic segmentation errors are partially predictable, we propose a compact formulation using confusion statistics of the trained classifier to refine (re-estimate) the initial pixel label hypotheses. The proposed strategy is contingent upon computing the classifier confusion probabilities for a given dataset and estimating a relevant prior on the object classes present in the image to be classified. We provide a procedure to robustly estimate the confusion probabilities and explore multiple prior definitions. Experiments are shown comparing performances on multiple challenging datasets using different priors to improve a state-of-the-art semantic segmentation classifier. This study demonstrates the potential to significantly improve semantic labeling and motivates future work for reliable label prior estimation from images.
@article{arxiv.1801.07674,
title = {A Classification Refinement Strategy for Semantic Segmentation},
author = {James W. Davis and Christopher Menart and Muhammad Akbar and Roman Ilin},
journal= {arXiv preprint arXiv:1801.07674},
year = {2018}
}