Convolutional Neural Networks (CNNs) trained with the Softmax loss are widely used classification models for several vision tasks. Typically, a learnable transformation (i.e. the classifier) is placed at the end of such models returning class scores that are further normalized into probabilities by Softmax. This learnable transformation has a fundamental role in determining the network internal feature representation. In this work we show how to extract from CNNs features with the properties of maximum inter-class separability and maximum intra-class compactness by setting the parameters of the classifier transformation as not train- able (i.e. fixed). We obtain features similar to what can be obtained with the well-known OCenter LossO [1] and other similar approaches but with several practical advantages including maximal exploitation of the available feature space representation, reduction in the number of net- work parameters, no need to use other auxiliary losses besides the Softmax. Our approach unifies and generalizes into a common approach two apparently different classes of methods regarding: discriminative features, pioneered by the Center Loss [1] and fixed classifiers, firstly evaluated in [2]. Preliminary qualitative experimental results provide some insight on the potentialities of our combined strategy.

Maximally Compact and Separated Features with Regular Polytope Networks / Pernici Federico, Bruni Matteo, Baecchi Claudio, Del Bimbo Alberto. - ELETTRONICO. - (2019), pp. 46-53. ((Intervento presentato al convegno Conference on Computer Vision and Pattern Recognition (CVPR) Workshops tenutosi a Long Beach, CA, USA nel 16-20 June 2019.

Maximally Compact and Separated Features with Regular Polytope Networks

Pernici Federico
;
Bruni Matteo;Baecchi Claudio;Del Bimbo Alberto
2019

Abstract

Convolutional Neural Networks (CNNs) trained with the Softmax loss are widely used classification models for several vision tasks. Typically, a learnable transformation (i.e. the classifier) is placed at the end of such models returning class scores that are further normalized into probabilities by Softmax. This learnable transformation has a fundamental role in determining the network internal feature representation. In this work we show how to extract from CNNs features with the properties of maximum inter-class separability and maximum intra-class compactness by setting the parameters of the classifier transformation as not train- able (i.e. fixed). We obtain features similar to what can be obtained with the well-known OCenter LossO [1] and other similar approaches but with several practical advantages including maximal exploitation of the available feature space representation, reduction in the number of net- work parameters, no need to use other auxiliary losses besides the Softmax. Our approach unifies and generalizes into a common approach two apparently different classes of methods regarding: discriminative features, pioneered by the Center Loss [1] and fixed classifiers, firstly evaluated in [2]. Preliminary qualitative experimental results provide some insight on the potentialities of our combined strategy.
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops
Conference on Computer Vision and Pattern Recognition (CVPR) Workshops
Long Beach, CA, USA
16-20 June 2019
Pernici Federico, Bruni Matteo, Baecchi Claudio, Del Bimbo Alberto
File in questo prodotto:
File Dimensione Formato  
Pernici_Maximally_Compact_and_Separated_Features_with_Regular_Polytope_Networks_CVPRW_2019_paper.pdf

accesso aperto

Tipologia: Pdf editoriale (Version of record)
Licenza: Open Access
Dimensione 1.12 MB
Formato Adobe PDF
1.12 MB Adobe PDF Visualizza/Apri

I documenti in FLORE 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/2158/1171654
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? ND
social impact