CLIMB uses a bounded hierarchical centroid memory with knowledge distillation to outperform prior OCSSL methods on Split CIFAR-100 and Split ImageNet-100 including irregular task distributions.
Unsupervised progressive learning and the STAM architecture.arXiv preprint arXiv:1904.02021,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CLIMB: Centroid-Based Hierarchical Memory for Online Continual Self-Supervised Learning
CLIMB uses a bounded hierarchical centroid memory with knowledge distillation to outperform prior OCSSL methods on Split CIFAR-100 and Split ImageNet-100 including irregular task distributions.