LSSKD trains compact classifiers with auxiliary self-supervised branches at each stage and past-epoch soft labels as targets, claiming teacher-free accuracy gains on classification benchmarks.
Data augmentation for improving deep learning in image classification problem,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A Layered Self-Supervised Knowledge Distillation Framework for Efficient Multimodal Learning on the Edge
LSSKD trains compact classifiers with auxiliary self-supervised branches at each stage and past-epoch soft labels as targets, claiming teacher-free accuracy gains on classification benchmarks.