Video action recognition models exhibit high performance on in-distribution data but struggle with distribution shifts in test data. To mitigate this issue, Unsupervised Domain Adaptation (UDA) methods have been proposed, consisting in training on labeled data from a source domain and incorporating unlabeled test data from a target domain to reduce the domain gap. This requires simultaneous access to data from both domains, which may not be practical in real-world scenarios due to privacy issues. A more practical approach called Source-Free Domain Adaptation (SFDA) has been recently proposed, which consists in adapting a well-trained source model using only unlabeled target data. However, existing SFDA methods are computationally intensive and designed for specific architectures. In this paper, we propose an approach called Lightweight Classification Module for Video Domain Adaptation (LCMV). LCMV is based on a backpropagation-free prototypical algorithm, which efficiently adapts a source model using unlabeled target data only. Results on two popular datasets, HMDB-UCFfull and EPIC-Kitchens-55, show significant improvements of LCMV compared to the previous state-of-the-art SFDA methods, and competitive results when compared to state-of-the-art UDA methods.
LCMV: Lightweight Classification Module for Video Domain Adaptation / Neubert, Julian; Planamente, Mirco; Plizzari, Chiara; Caputo, Barbara. - 14234:(2023), pp. 270-282. (Intervento presentato al convegno 22nd International Conference on Image Analysis and Processing (ICIAP 2023) tenutosi a Udine (ITA) nel September 11–15, 2023) [10.1007/978-3-031-43153-1_23].
LCMV: Lightweight Classification Module for Video Domain Adaptation
Mirco Planamente;Chiara Plizzari;Barbara Caputo
2023
Abstract
Video action recognition models exhibit high performance on in-distribution data but struggle with distribution shifts in test data. To mitigate this issue, Unsupervised Domain Adaptation (UDA) methods have been proposed, consisting in training on labeled data from a source domain and incorporating unlabeled test data from a target domain to reduce the domain gap. This requires simultaneous access to data from both domains, which may not be practical in real-world scenarios due to privacy issues. A more practical approach called Source-Free Domain Adaptation (SFDA) has been recently proposed, which consists in adapting a well-trained source model using only unlabeled target data. However, existing SFDA methods are computationally intensive and designed for specific architectures. In this paper, we propose an approach called Lightweight Classification Module for Video Domain Adaptation (LCMV). LCMV is based on a backpropagation-free prototypical algorithm, which efficiently adapts a source model using unlabeled target data only. Results on two popular datasets, HMDB-UCFfull and EPIC-Kitchens-55, show significant improvements of LCMV compared to the previous state-of-the-art SFDA methods, and competitive results when compared to state-of-the-art UDA methods.File | Dimensione | Formato | |
---|---|---|---|
ICIAP23 (9).pdf
Open Access dal 06/09/2024
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
PUBBLICO - Tutti i diritti riservati
Dimensione
1.45 MB
Formato
Adobe PDF
|
1.45 MB | Adobe PDF | Visualizza/Apri |
978-3-031-43153-1_23.pdf
non disponibili
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
629.28 kB
Formato
Adobe PDF
|
629.28 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2981187