We propose a network architecture to perform efficient scene understanding. This work presents three main novelties: the first is a module named Improved Guided Upsampling Module that can replace in toto the decoder part in common semantic segmentation networks. Our second contribution is the introduction of a new module based on spatial sampling to perform Instance Segmentation. It provides a very fast instance segmentation needing only a simple post-processing step at inference time. Finally, we propose a novel efficient network design that includes the new modules and test it against different datasets for outdoor scene understanding. To our knowledge, our network is one of the most efficient architectures for scene understanding published to date, furthermore being 8.6% more accurate than the fastest competitor on semantic segmentation and almost five times faster than the most efficient network for instance segmentation.

Mazzini, D., Schettini, R. (2019). Spatial sampling network for fast scene understanding. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (pp.1286-1296). IEEE [10.1109/CVPRW.2019.00168].

Spatial sampling network for fast scene understanding

Mazzini D.;Schettini R.
2019

Abstract

We propose a network architecture to perform efficient scene understanding. This work presents three main novelties: the first is a module named Improved Guided Upsampling Module that can replace in toto the decoder part in common semantic segmentation networks. Our second contribution is the introduction of a new module based on spatial sampling to perform Instance Segmentation. It provides a very fast instance segmentation needing only a simple post-processing step at inference time. Finally, we propose a novel efficient network design that includes the new modules and test it against different datasets for outdoor scene understanding. To our knowledge, our network is one of the most efficient architectures for scene understanding published to date, furthermore being 8.6% more accurate than the fastest competitor on semantic segmentation and almost five times faster than the most efficient network for instance segmentation.
paper
Computer vision; Semantics
English
32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019 - 16-17 June 2019
2019
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
9781728125060
2019
2019-June
1286
1296
9025478
none
Mazzini, D., Schettini, R. (2019). Spatial sampling network for fast scene understanding. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (pp.1286-1296). IEEE [10.1109/CVPRW.2019.00168].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/10281/470942
Citazioni
  • Scopus 20
  • ???jsp.display-item.citation.isi??? 11
Social impact