Heterogeneous Auto-Similarities of Characteristics


Capturing the essential characteristics of visual objects by considering how their features are inter-related is a recent philosophy of object classification. We embed this principle in a novel image descriptor, dubbed Heterogeneous Auto-Similarities of Characteristics (HASC). HASC is applied to heterogeneous dense features maps, encoding linear relations by covariances and nonlinear associations through information-theoretic measures such as mutual information and entropy. In this way, highly complex structural information can be expressed in a compact, scale invariant and robust manner.



Code available

Download HASC code (Beta Version)

Download HASC code (Beta Version) - Caltech 101 Experiment



  • M. San Biagio, M. Crocco, M. Cristani, S. Martelli and V. Murino
    "Heterogeneous Auto-Similarities of Characteristics (HASC): Exploiting Relational Information for Classification"
    International Conference on Computer Vision, (ICCV), 2013 [PDF]