Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches

July 08, 2019 ยท Declared Dead ยท ๐Ÿ› 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Vincenzo Lomonaco, Davide Maltoni, Lorenzo Pellegrini arXiv ID 1907.03799 Category cs.LG: Machine Learning Cross-listed cs.CV, cs.NE, stat.ML Citations 71 Venue 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Last Checked 4 months ago
Abstract
Robotic vision is a field where continual learning can play a significant role. An embodied agent operating in a complex environment subject to frequent and unpredictable changes is required to learn and adapt continuously. In the context of object recognition, for example, a robot should be able to learn (without forgetting) objects of never before seen classes as well as improving its recognition capabilities as new instances of already known classes are discovered. Ideally, continual learning should be triggered by the availability of short videos of single objects and performed on-line on on-board hardware with fine-grained updates. In this paper, we introduce a novel continual learning protocol based on the CORe50 benchmark and propose two rehearsal-free continual learning techniques, CWR* and AR1*, that can learn effectively even in the challenging case of nearly 400 small non-i.i.d. incremental batches. In particular, our experiments show that AR1* can outperform other state-of-the-art rehearsal-free techniques by more than 15% accuracy in some cases, with a very light and constant computational and memory overhead across training batches.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted