In this work, we attempted to extend the thought and showcase a way forward for the Self-supervised Learning (SSL) learning paradigm by combining contrastive learning, self-distillation (knowledge distillation) and masked data modelling, the three major SSL frameworks, to learn a joint and coordinated representation. The proposed technique of SSL learns by the collaborative power of different learning objectives of SSL. Hence to jointly learn the different SSL objectives we proposed a new SSL architecture KDC-MAE, a complementary masking strategy to learn the modular correspondence, and a weighted way to combine them coordinately. Experimental results conclude that the contrastive masking correspondence along with the KD learning objective has lent a hand to performing better learning for multiple modalities over multiple tasks.
@article{arxiv.2411.12270,
title = {KDC-MAE: Knowledge Distilled Contrastive Mask Auto-Encoder},
author = {Maheswar Bora and Saurabh Atreya and Aritra Mukherjee and Abhijit Das},
journal= {arXiv preprint arXiv:2411.12270},
year = {2024}
}