We present SIMCO, the first agnostic multi-class object counting approach.SIMCO starts by detecting foreground objects through a novel Mask RCNN-basedarchitecture trained beforehand (just once) on a brand-new synthetic 2D shapedataset, InShape; the idea is to highlight every object resembling a primitive2D shape (circle, square, rectangle, etc.). Each object detected is describedby a low-dimensional embedding, obtained from a novel similarity-based headbranch; this latter implements a triplet loss, encouraging similar objects(same 2D shape + color and scale) to map close. Subsequently, SIMCO uses thisembedding for clustering, so that different types of objects can emerge and becounted, making SIMCO the very first multi-class unsupervised counter.Experiments show that SIMCO provides state-of-the-art scores on countingbenchmarks and that it can also help in many challenging image understandingtasks.

SIMCO: SIMilarity-based object COunting

Marco Godi;Christian Joppi
;
Andrea Giachetti;Marco Cristani
2019-01-01

Abstract

We present SIMCO, the first agnostic multi-class object counting approach.SIMCO starts by detecting foreground objects through a novel Mask RCNN-basedarchitecture trained beforehand (just once) on a brand-new synthetic 2D shapedataset, InShape; the idea is to highlight every object resembling a primitive2D shape (circle, square, rectangle, etc.). Each object detected is describedby a low-dimensional embedding, obtained from a novel similarity-based headbranch; this latter implements a triplet loss, encouraging similar objects(same 2D shape + color and scale) to map close. Subsequently, SIMCO uses thisembedding for clustering, so that different types of objects can emerge and becounted, making SIMCO the very first multi-class unsupervised counter.Experiments show that SIMCO provides state-of-the-art scores on countingbenchmarks and that it can also help in many challenging image understandingtasks.
Computer Science - Computer Vision and Pattern Recognition; Computer Science - Computer Vision and Pattern Recognition; Computer Science - Learning
File in questo prodotto:
File Dimensione Formato  
SIMCO Similarity-Based Object Counting.pdf

solo utenti autorizzati

Tipologia: Documento in Post-print
Licenza: Accesso ristretto
Dimensione 4.15 MB
Formato Adobe PDF
4.15 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11562/1012009
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact