Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning.
Colorado J. ReedRitwik GuptaShufan LiSarah BrockmanChristopher FunkBrian ClippKurt KeutzerSalvatore CandidoMatt UyttendaeleTrevor DarrellPublished in: ICCV (2023)
Keyphrases
- multiscale
- scale space
- scale selection
- learning process
- learning systems
- online learning
- multiscale analysis
- single scale
- edge detection
- knowledge acquisition
- reinforcement learning
- learning tasks
- inductive inference
- feedforward neural networks
- learning algorithm
- neural network
- supervised learning
- prior knowledge
- multiresolution
- back propagation
- multiple scales
- multiple representations
- image processing