SPARROW: Semantically Coherent Prototypes for Image Classification

Stefan Kraft, Klaus Broelemann, Andreas Theissler, Gjergji Kasneci

Research output: Contribution to conferencePaperpeer-review

4 Scopus citations


Current prototype-based classification often leads to prototypes with overlapping semantics where several prototypes are similar to the same image parts. Also, single prototypes tend to activate highly on a mixture of semantically different image parts. This impedes interpretability since the nature of the connections between the parts is unknown. We propose a framework that is comprised of two key elements: (i) A novel method which leads to semantically coherent prototypes and (ii) an evaluation protocol which is based on part annotations and allows to quantitatively compare the explanatory capacity of prototypes from different methods. We demonstrate the viability of our framework by comparing our method to a standard prototype-based classification method and show that our method is capable of producing prototypes of superior interpretability.

Original languageEnglish
StatePublished - 2021
Externally publishedYes
Event32nd British Machine Vision Conference, BMVC 2021 - Virtual, Online
Duration: 22 Nov 202125 Nov 2021


Conference32nd British Machine Vision Conference, BMVC 2021
CityVirtual, Online


Dive into the research topics of 'SPARROW: Semantically Coherent Prototypes for Image Classification'. Together they form a unique fingerprint.

Cite this