Image Parsing with a Wide Range of Classes and Scene-Level Context
This improves image parsing accuracy and class coverage for computer vision applications, but it is incremental.
The paper tackles scene parsing by merging classifier likelihoods and incorporating global semantic context, achieving state-of-the-art performance on SIFTflow and near-record results on LMSun.
This paper presents a nonparametric scene parsing approach that improves the overall accuracy, as well as the coverage of foreground classes in scene images. We first improve the label likelihood estimates at superpixels by merging likelihood scores from different probabilistic classifiers. This boosts the classification performance and enriches the representation of less-represented classes. Our second contribution consists of incorporating semantic context in the parsing process through global label costs. Our method does not rely on image retrieval sets but rather assigns a global likelihood estimate to each label, which is plugged into the overall energy function. We evaluate our system on two large-scale datasets, SIFTflow and LMSun. We achieve state-of-the-art performance on the SIFTflow dataset and near-record results on LMSun.