Availability of labelled data is the major obstacle to the deployment of deep learning algorithms for computer vision tasks in new domains. The fact that many frameworks adopted to solve different tasks share the same architecture suggests that there should be a way of reusing the knowledge learned in a specific setting to solve novel tasks with limited or no additional supervision. In this work, we first show that such knowledge can be shared across tasks by learning a mapping between task-specific deep features in a given domain. Then, we show that this mapping function, implemented by a neural network, is able to generalize to novel unseen domains. Besides, we propose a set of strategies to constrain the learned feature spaces, to ease learning and increase the generalization capability of the mapping network, thereby considerably improving the final performance of our framework. Our proposal obtains compelling results in challenging synthetic-to-real adaptation scenarios by transferring knowledge between monocular depth estimation and semantic segmentation tasks.

Learning Good Features to Transfer Across Tasks and Domains / Pierluigi Zama Ramirez; Adriano Cardace; Luca De Luigi; Alessio Tonioni; Samuele Salti; Luigi Di Stefano. - In: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. - ISSN 0162-8828. - ELETTRONICO. - 45:(2023), pp. 9981-9995. [10.1109/TPAMI.2023.3240316]

Learning Good Features to Transfer Across Tasks and Domains

Pierluigi Zama Ramirez;Adriano Cardace;Luca De Luigi;Alessio Tonioni;Samuele Salti;Luigi Di Stefano
2023

Abstract

Availability of labelled data is the major obstacle to the deployment of deep learning algorithms for computer vision tasks in new domains. The fact that many frameworks adopted to solve different tasks share the same architecture suggests that there should be a way of reusing the knowledge learned in a specific setting to solve novel tasks with limited or no additional supervision. In this work, we first show that such knowledge can be shared across tasks by learning a mapping between task-specific deep features in a given domain. Then, we show that this mapping function, implemented by a neural network, is able to generalize to novel unseen domains. Besides, we propose a set of strategies to constrain the learned feature spaces, to ease learning and increase the generalization capability of the mapping network, thereby considerably improving the final performance of our framework. Our proposal obtains compelling results in challenging synthetic-to-real adaptation scenarios by transferring knowledge between monocular depth estimation and semantic segmentation tasks.
2023
Learning Good Features to Transfer Across Tasks and Domains / Pierluigi Zama Ramirez; Adriano Cardace; Luca De Luigi; Alessio Tonioni; Samuele Salti; Luigi Di Stefano. - In: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. - ISSN 0162-8828. - ELETTRONICO. - 45:(2023), pp. 9981-9995. [10.1109/TPAMI.2023.3240316]
Pierluigi Zama Ramirez; Adriano Cardace; Luca De Luigi; Alessio Tonioni; Samuele Salti; Luigi Di Stefano
File in questo prodotto:
File Dimensione Formato  
2301.11310.pdf

accesso aperto

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 5.19 MB
Formato Adobe PDF
5.19 MB Adobe PDF Visualizza/Apri

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/11585/955900
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 0
social impact