CA-DSSL enables effective self-supervised pretraining for 396K-parameter MCU backbones, reaching 62.7% linear-probe accuracy on CIFAR-100 and 94% of supervised performance while fitting in 378 KB INT8.
International Conference on Machine Learning , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
Covariance structure and coordinate heterogeneity in InfoNCE embeddings control binary quantization fidelity, with off-diagonals contributing 30-50% of signal and heterogeneity determining rotation benefit and bit utility under a Gaussian model.
citing papers explorer
-
TinySSL: Distilled Self-Supervised Pretraining for Sub-Megabyte MCU Models
CA-DSSL enables effective self-supervised pretraining for 396K-parameter MCU backbones, reaching 62.7% linear-probe accuracy on CIFAR-100 and 94% of supervised performance while fitting in 378 KB INT8.
-
Covariance Structure and Coordinate Heterogeneity Govern Binary Quantization of Contrastive Embeddings
Covariance structure and coordinate heterogeneity in InfoNCE embeddings control binary quantization fidelity, with off-diagonals contributing 30-50% of signal and heterogeneity determining rotation benefit and bit utility under a Gaussian model.