KDC-MAE: Knowledge Distilled Contrastive Mask Auto-Encoder

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bora, Maheswar, Atreya, Saurabh, Mukherjee, Aritra, Das, Abhijit
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910705218748416
author Bora, Maheswar
Atreya, Saurabh
Mukherjee, Aritra
Das, Abhijit
author_facet Bora, Maheswar
Atreya, Saurabh
Mukherjee, Aritra
Das, Abhijit
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12270
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle KDC-MAE: Knowledge Distilled Contrastive Mask Auto-Encoder
Bora, Maheswar
Atreya, Saurabh
Mukherjee, Aritra
Das, Abhijit
Computer Vision and Pattern Recognition
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.
title KDC-MAE: Knowledge Distilled Contrastive Mask Auto-Encoder
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.12270