Survey of continual learning for image classification
Survey of continual learning for image classification
Online Continual Learning in Image Classification: An Empirical Survey
arXiv paper abstract https://arxiv.org/abs/2101.10423
arXiv PDF paper https://arxiv.org/pdf/2101.10423.pdf
... challenges of continual learning is to avoid catastrophic forgetting (CF), i.e., forgetting old tasks in the presence of more recent tasks.
... many methods and tricks have been introduced to address this problem, but many have not been fairly and systematically compared under a variety of realistic and practical settings.
... survey aims to
(1) compare state-of-the-art methods such as MIR, iCARL, and GDumb and determine which works best at different experimental settings;
(2) determine if the best class incremental methods are also competitive in domain incremental setting;
(3) evaluate the performance of 7 simple but effective trick such as "review" trick and nearest class mean (NCM) classifier to assess their relative impact.
Regarding (1)
... iCaRL remains competitive when the memory buffer is small
... GDumb outperforms many recently proposed methods in medium-size datasets
... MIR performs the best in larger-scale datasets.
For (2),
... GDumb performs quite poorly
... MIR -- already competitive for (1) -- is also strongly competitive in this very different but important setting.
Overall, this allows us to conclude that MIR is overall a strong and versatile method across a wide variety of settings.
For (3),
we find that all 7 tricks are beneficial, and when augmented with the "review" trick and NCM classifier,
MIR produces performance levels that bring online continual learning much closer to its ultimate goal of matching offline training.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments