Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908932057858048 |
|---|---|
| author | Tang, Maofeng Cozma, Andrei Georgiou, Konstantinos Qi, Hairong |
| author_facet | Tang, Maofeng Cozma, Andrei Georgiou, Konstantinos Qi, Hairong |
| contents | Remote sensing images present unique challenges to image analysis due to the extensive geographic coverage, hardware limitations, and misaligned multi-scale images. This paper revisits the classical multi-scale representation learning problem but under the general framework of self-supervised learning for remote sensing image understanding. We present Cross-Scale MAE, a self-supervised model built upon the Masked Auto-Encoder (MAE).During pre-training, Cross-Scale MAE employs scale augmentation techniques and enforces cross-scale consistency constraints through both contrastive and generative losses to ensure consistent and meaningful representations well-suited for a wide range of downstream tasks. Further, our implementation leverages the xFormers library to accelerate network pre-training on a single GPU while maintaining the quality of learned representations. Experimental evaluations demonstrate that Cross-Scale MAE exhibits superior performance compared to standard MAE and other state-of-the-art remote sensing MAE methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_15855 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensing Tang, Maofeng Cozma, Andrei Georgiou, Konstantinos Qi, Hairong Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing Remote sensing images present unique challenges to image analysis due to the extensive geographic coverage, hardware limitations, and misaligned multi-scale images. This paper revisits the classical multi-scale representation learning problem but under the general framework of self-supervised learning for remote sensing image understanding. We present Cross-Scale MAE, a self-supervised model built upon the Masked Auto-Encoder (MAE).During pre-training, Cross-Scale MAE employs scale augmentation techniques and enforces cross-scale consistency constraints through both contrastive and generative losses to ensure consistent and meaningful representations well-suited for a wide range of downstream tasks. Further, our implementation leverages the xFormers library to accelerate network pre-training on a single GPU while maintaining the quality of learned representations. Experimental evaluations demonstrate that Cross-Scale MAE exhibits superior performance compared to standard MAE and other state-of-the-art remote sensing MAE methods. |
| title | Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensing |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing |
| url | https://arxiv.org/abs/2401.15855 |