An efficient mid-level representation for facial attributes and tattoo recognition

When implementing real-world computer vision systems, researchers can use mid-level representations as a tool to adjust the trade-off between accuracy and efficiency. Unfortunately, existing mid-level representations that improve accuracy tend to decrease efficiency, or are specifically tailored to work well within one pipeline or vision problem at the exclusion of others. We introduce a novel, efficient mid-level representation that improves classification efficiency without sacrificing accuracy. Our Exemplar Codes are based on linear classifiers and probability normalization from extreme value theory.


Here, we provide 73 attribute scores for all images within LFW, similar to the Attribute Face System in [1]. These scores were extracted using our Cascaded Exemplar Codes system on automatically aligned images of LFW, see here: Download the Paper Attributes for LFW Aligned LFW Images