Automatically understanding emotions from visual data is a fundamental task for human behaviour understanding. While models devised for Facial Expression Recognition (FER) have demonstrated excellent performances on many datasets, they often suffer from severe performance degradation when trained and tested on different datasets due to domain shift. In addition, as face images are considered highly sensitive data, the accessibility to large-scale datasets for model training is often denied. In this work, we tackle the above-mentioned problems by proposing the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for FER. Our method exploits self-supervised pretraining to learn good feature representations from the target data and proposes a novel and robust cluster-level pseudo-labelling strategy that accounts for in-cluster statistics. We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER, and is on par with methods addressing FER in the UDA setting.

Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition / Conti, Alessandro; Rota, Paolo; Wang, Yiming; Ricci, Elisa. - (2022). (Intervento presentato al convegno British Machine Vision Conference tenutosi a London nel 21-11-2022) [10.48550/ARXIV.2210.05246].

Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition

Conti, Alessandro;Rota, Paolo;Wang, Yiming;Ricci, Elisa
2022-01-01

Abstract

Automatically understanding emotions from visual data is a fundamental task for human behaviour understanding. While models devised for Facial Expression Recognition (FER) have demonstrated excellent performances on many datasets, they often suffer from severe performance degradation when trained and tested on different datasets due to domain shift. In addition, as face images are considered highly sensitive data, the accessibility to large-scale datasets for model training is often denied. In this work, we tackle the above-mentioned problems by proposing the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for FER. Our method exploits self-supervised pretraining to learn good feature representations from the target data and proposes a novel and robust cluster-level pseudo-labelling strategy that accounts for in-cluster statistics. We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER, and is on par with methods addressing FER in the UDA setting.
2022
British Machine Vision Conference
London
The British Machine Vision Association
Conti, Alessandro; Rota, Paolo; Wang, Yiming; Ricci, Elisa
Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition / Conti, Alessandro; Rota, Paolo; Wang, Yiming; Ricci, Elisa. - (2022). (Intervento presentato al convegno British Machine Vision Conference tenutosi a London nel 21-11-2022) [10.48550/ARXIV.2210.05246].
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/11572/399469
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

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