Trinet: Stabilizing Self-Supervised Learning From Complete or Slow Collapse
Lixin Cao, Jun Wang, Ben Yang, Dan Su, Dong Yu
Abstract
Self-supervised learning (SSL) models confront challenges of abrupt informational collapse or slow dimensional collapse. We propose TriNet, which introduces a novel triple-branch architecture for preventing collapse and stabilizing the pretraining. TriNet learns the SSL latent embedding space and incorporates it to a higher level space for predicting pseudo target vectors generated by a frozen teacher. Our experimental results show that the proposed method notably stabilizes and accelerates pre-training and achieves a relative word error rate reduction (WERR) of 6.06% compared to the state-of- the-art (SOTA) Data2vec for a downstream benchmark ASR task. We will release our code at https://github.com/tencent-ailab/.
BibTeX
@inproceedings{icassp2023_trinetstabilizin,
title = {Trinet: Stabilizing Self-Supervised Learning From Complete or Slow Collapse},
author = {Lixin Cao and Jun Wang and Ben Yang and Dan Su and Dong Yu},
booktitle = {ICASSP 2023},
year = {2023}
}