Most of the leading Convolutional Neural Network (CNN) models for semantic segmentation exploit a large number of pixel–level annotations. Such a human based labeling requires a considerable effort that complicates the creation of large–scale datasets. In this paper, we propose a deep learning approach that uses bounding box annotations to train a semantic segmentation network. Indeed, the bounding box supervision, even though less accurate, is a valuable alternative, effective in reducing the dataset collection costs. The proposed method is based on a two stage training procedure: first, a deep neural network is trained to distinguish the relevant object from the background inside a given bounding box; then, the output of the network is used to provide a weak supervision for a multi–class segmentation CNN. The performances of our approach have been assessed on the Pascal–VOC 2012 segmentation dataset, obtaining competitive results compared to a fully supervised setting.

Bonechi, S., Andreini, P., Bianchini, M., Scarselli, F. (2018). Generating Bounding Box Supervision for Semantic Segmentation with Deep Learning. In S.F. Pancioni L. (a cura di), ANNPR 2018: Artificial Neural Networks in Pattern Recognition (pp. 190-200). Cham : Springer [10.1007/978-3-319-99978-4_15].

Generating Bounding Box Supervision for Semantic Segmentation with Deep Learning

Bonechi, Simone;Andreini, Paolo
;
Bianchini, Monica;Scarselli, Franco
2018-01-01

Abstract

Most of the leading Convolutional Neural Network (CNN) models for semantic segmentation exploit a large number of pixel–level annotations. Such a human based labeling requires a considerable effort that complicates the creation of large–scale datasets. In this paper, we propose a deep learning approach that uses bounding box annotations to train a semantic segmentation network. Indeed, the bounding box supervision, even though less accurate, is a valuable alternative, effective in reducing the dataset collection costs. The proposed method is based on a two stage training procedure: first, a deep neural network is trained to distinguish the relevant object from the background inside a given bounding box; then, the output of the network is used to provide a weak supervision for a multi–class segmentation CNN. The performances of our approach have been assessed on the Pascal–VOC 2012 segmentation dataset, obtaining competitive results compared to a fully supervised setting.
2018
978-3-319-99977-7
978-3-319-99978-4
Bonechi, S., Andreini, P., Bianchini, M., Scarselli, F. (2018). Generating Bounding Box Supervision for Semantic Segmentation with Deep Learning. In S.F. Pancioni L. (a cura di), ANNPR 2018: Artificial Neural Networks in Pattern Recognition (pp. 190-200). Cham : Springer [10.1007/978-3-319-99978-4_15].
File in questo prodotto:
File Dimensione Formato  
Generating Bounding Box Supervision for Semantic Segmentation with Deep Learning.pdf

non disponibili

Descrizione: preprint
Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 3.17 MB
Formato Adobe PDF
3.17 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/11365/1062270