The recognition of logos can be useful in developing autonomous checkout systems, or monitoring brand presence and advertisement in shopping malls. The continuous generation and update of new brand logos imposes the definition of a flexible solution to the problem. We therefore define a two-stage logo recognition system composed of an agnostic logo detector, to locate image regions that possess generic logo-like characteristics, and an incremental logo classifier, to progressively update the set of known logo classes. We investigate our solution's sensitivity to regularization and availability of training samples, and we develop two alternative techniques for model compression. Results are presented and compared with state of the art solutions, showing promising results. Our code is made available for public download.
Bianco, S., Buzzelli, M., Giudice, G. (2022). Incremental Two-Stage Logo Recognition with Knowledge Distillation. In IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin (pp.1-6). IEEE Computer Society [10.1109/ICCE-Berlin56473.2022.9937102].
Incremental Two-Stage Logo Recognition with Knowledge Distillation
Bianco S.;Buzzelli M.;
2022
Abstract
The recognition of logos can be useful in developing autonomous checkout systems, or monitoring brand presence and advertisement in shopping malls. The continuous generation and update of new brand logos imposes the definition of a flexible solution to the problem. We therefore define a two-stage logo recognition system composed of an agnostic logo detector, to locate image regions that possess generic logo-like characteristics, and an incremental logo classifier, to progressively update the set of known logo classes. We investigate our solution's sensitivity to regularization and availability of training samples, and we develop two alternative techniques for model compression. Results are presented and compared with state of the art solutions, showing promising results. Our code is made available for public download.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
