RECALL achieves rehearsal-free continual learning for object classification by logit recall before new training, regression regularization, Mahalanobis loss on known categories, and new heads per sequence, outperforming prior methods on CORe50, iCIFAR-100, and the introduced HOWS-CL-25 dataset.
The mnist database of handwritten digits,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2022 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RECALL: Rehearsal-free Continual Learning for Object Classification
RECALL achieves rehearsal-free continual learning for object classification by logit recall before new training, regression regularization, Mahalanobis loss on known categories, and new heads per sequence, outperforming prior methods on CORe50, iCIFAR-100, and the introduced HOWS-CL-25 dataset.