NCPTM-CIL applies a dynamic equiangular-tight-frame classifier and pull-and-push loss to pre-trained model-based class-incremental learning and reports state-of-the-art average accuracy on four benchmarks.
MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing Pre-Trained Model-Based Class-Incremental Learning through Neural Collapse
NCPTM-CIL applies a dynamic equiangular-tight-frame classifier and pull-and-push loss to pre-trained model-based class-incremental learning and reports state-of-the-art average accuracy on four benchmarks.