INTRODUCTION
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.
![](https://www.iit.it/documents/1452990/1461321/Heterogeneous_Auto-Similarities_of_Characteristics_cover.png/81fa782a-81c9-fa6c-c2b4-2d5511b2223a?t=1655453351769)