The Places dataset is proposed for scene recognition and contains more than 2.5 million images covering more than 205 scene categories with more than 5,000 images per category.
Source: Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
Image Source: http://places.csail.mit.edu/browser.html
Variants: Places2, Places2 val, Places
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Cross-Domain Few-Shot | StyleAdv-FT | StyleAdv: Meta Style Adversarial Training … | 2023-02-18 |
| Cross-Domain Few-Shot | StyleAdv | StyleAdv: Meta Style Adversarial Training … | 2023-02-18 |
| Cross-Domain Few-Shot | AFA | Adversarial Feature Augmentation for Cross-domain … | 2022-08-23 |
| Cross-Domain Few-Shot | wave-SAN | Wave-SAN: Wavelet based Style Augmentation … | 2022-03-15 |
| Cross-Domain Few-Shot | ATA-FT | Cross-Domain Few-Shot Classification via Adversarial … | 2021-04-29 |
| Cross-Domain Few-Shot | ATA | Cross-Domain Few-Shot Classification via Adversarial … | 2021-04-29 |
| Cross-Domain Few-Shot | FWT | Cross-Domain Few-Shot Classification via Learned … | 2020-01-23 |
| Cross-Domain Few-Shot | BSCD-FSL | A Broader Study of Cross-Domain … | 2019-12-16 |
Recent papers with results on this dataset: