Image translation with convolutional neural networks has recently been used as an approach to multimodal change detection. Existing approaches train the networks by exploiting supervised information of the change areas, which, however, is not always available. A main challenge in the unsupervised problem setting is to avoid that change pixels affect the learning of the translation function. We propose two new network architectures trained with loss functions weighted by priors that reduce the impact of change pixels on the learning objective. The change prior is derived in an unsupervised fashion from relational pixel information captured by domain-specific affinity matrices. Specifically, we use the vertex degrees associated with an absolute affinity difference matrix and demonstrate their utility in combination with cycle consistency and adversarial training. The proposed neural networks are compared with the state-of-the-art algorithms. Experiments conducted on three real data sets show the effectiveness of our methodology.
Deep Image Translation with an Affinity-Based Change Prior for Unsupervised Multimodal Change Detection
Luppino L. T.;Moser G.;Serpico S. B.;
2022-01-01
Abstract
Image translation with convolutional neural networks has recently been used as an approach to multimodal change detection. Existing approaches train the networks by exploiting supervised information of the change areas, which, however, is not always available. A main challenge in the unsupervised problem setting is to avoid that change pixels affect the learning of the translation function. We propose two new network architectures trained with loss functions weighted by priors that reduce the impact of change pixels on the learning objective. The change prior is derived in an unsupervised fashion from relational pixel information captured by domain-specific affinity matrices. Specifically, we use the vertex degrees associated with an absolute affinity difference matrix and demonstrate their utility in combination with cycle consistency and adversarial training. The proposed neural networks are compared with the state-of-the-art algorithms. Experiments conducted on three real data sets show the effectiveness of our methodology.File | Dimensione | Formato | |
---|---|---|---|
22.tgrs.luppino.compressed.pdf
accesso aperto
Descrizione: Articolo su rivista
Tipologia:
Documento in Post-print
Dimensione
9.71 MB
Formato
Adobe PDF
|
9.71 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.