Bhattacharyya, Apratim ; Mahajan, Shweta ; Fritz, Mario ; Schiele, Bernt ; Roth, Stefan (2020)
Normalizing Flows With Multi-Scale Autoregressive Priors.
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. virtual Conference (14.-19.06.2020)
doi: 10.1109/CVPR42600.2020.00844
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Flow-based generative models are an important class of exact inference models that admit efficient inference and sampling for image synthesis. Owing to the efficiency constraints on the design of the flow layers, e.g. split coupling flow layers in which approximately half the pixels do not undergo further transformations, they have limited expressiveness for modeling long-range data dependencies compared to autoregressive models that rely on conditional pixel-wise generation. In this work, we improve the representational power of flow-based models by introducing channel-wise dependencies in their latent space through multi-scale autoregressive priors (mAR). Our mAR prior for models with split coupling flow layers (mAR-SCF) can better capture dependencies in complex multimodal data. The resulting model achieves state-of-the-art density estimation results on MNIST, CIFAR-10, and ImageNet. Furthermore, we show that mAR-SCF allows for improved image generation quality, with gains in FID and Inception scores compared to state-of-the-art flow-based models.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2020 |
| Autor(en): | Bhattacharyya, Apratim ; Mahajan, Shweta ; Fritz, Mario ; Schiele, Bernt ; Roth, Stefan |
| Art des Eintrags: | Bibliographie |
| Titel: | Normalizing Flows With Multi-Scale Autoregressive Priors |
| Sprache: | Englisch |
| Publikationsjahr: | 5 August 2020 |
| Verlag: | IEEE |
| Buchtitel: | Proceedings: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition |
| Veranstaltungstitel: | 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition |
| Veranstaltungsort: | virtual Conference |
| Veranstaltungsdatum: | 14.-19.06.2020 |
| DOI: | 10.1109/CVPR42600.2020.00844 |
| URL / URN: | https://openaccess.thecvf.com/content_CVPR_2020/papers/Bhatt... |
| Kurzbeschreibung (Abstract): | Flow-based generative models are an important class of exact inference models that admit efficient inference and sampling for image synthesis. Owing to the efficiency constraints on the design of the flow layers, e.g. split coupling flow layers in which approximately half the pixels do not undergo further transformations, they have limited expressiveness for modeling long-range data dependencies compared to autoregressive models that rely on conditional pixel-wise generation. In this work, we improve the representational power of flow-based models by introducing channel-wise dependencies in their latent space through multi-scale autoregressive priors (mAR). Our mAR prior for models with split coupling flow layers (mAR-SCF) can better capture dependencies in complex multimodal data. The resulting model achieves state-of-the-art density estimation results on MNIST, CIFAR-10, and ImageNet. Furthermore, we show that mAR-SCF allows for improved image generation quality, with gains in FID and Inception scores compared to state-of-the-art flow-based models. |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Visuelle Inferenz DFG-Graduiertenkollegs DFG-Graduiertenkollegs > Graduiertenkolleg 1994 Adaptive Informationsaufbereitung aus heterogenen Quellen |
| Hinterlegungsdatum: | 08 Mär 2022 07:50 |
| Letzte Änderung: | 08 Mär 2022 07:50 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum