paper-with-me

Papers

Bootstrapping Vision-language Models for Self-supervised Remote Physiological Measurement

2024-07-11 · Zijie Yue, Miaojing Shi, Hanli Wang, Shuai Ding, Qijun Chen, Shanlin Yang

Facial video-based remote physiological measurement is a promising research area for detecting human vital signs (e.g., heart rate, respiration frequency) in a non-contact way. Conventional approaches are mostly supervised learning, requiring extensive collections of facial videos and synchronously recorded photoplethysmography (PPG) signals. To tackle it, self-supervised learning has recently gained attentions; due to the lack of ground truth PPG signals, its performance is however limited. In this paper, we propose a novel self-supervised framework that successfully integrates the popular vision-language models (VLMs) into the remote physiological measurement task. Given a facial video, we first augment its positive and negative video samples with varying rPPG signal frequencies. Next, we introduce a frequency-oriented vision-text pair generation method by carefully creating contrastive spatio-temporal maps from positive and negative samples and designing proper text prompts to describe their relative ratios of signal frequencies. A pre-trained VLM is employed to extract features for these formed vision-text pairs and estimate rPPG signals thereafter. We develop a series of generative and contrastive learning mechanisms to optimize the VLM, including the text-guided visual map reconstruction task, the vision-text contrastive learning task, and the frequency contrastive and ranking task. Overall, our method for the first time adapts VLMs to digest and align the frequency-related knowledge in vision and text modalities. Extensive experiments on four benchmark datasets demonstrate that it significantly outperforms state of the art self-supervised methods.

📄 PDF Abstract BibTeX arXiv:2407.08507

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningPhotoplethysmography (PPG)Self-Supervised Learning

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Mean BERTs make erratic language teachers: the effectiveness of latent bootstrapping in low-resource settings

2023-10-30 · David Samuel

This paper explores the use of latent bootstrapping, an alternative self-supervision technique, for pretraining language models. Unlike the typical practice of using self-supervision on discrete subwords, latent bootstra…

Co-training an Unsupervised Constituency Parser with Weak Supervision

2021-10-05 · Findings (ACL) 2022 5 · Nickil Maveli, Shay B. Cohen

We introduce a method for unsupervised parsing that relies on bootstrapping classifiers to identify if a node dominates a specific span in a sentence. There are two types of classifiers, an inside classifier that acts on…

Constituency Grammar InductionInductive BiasSentence

Co-training an Unsupervised Constituency Parser with Weak Supervision

2021-11-16 · ACL ARR November 2021 11 · Anonymous

We introduce a method for unsupervised parsing that relies on bootstrapping classifiers to identify if a node dominates a specific span in a sentence. There are two types of classifiers, an inside classifier that acts on…

Inductive BiasSentence

Self-supervised Learning in Remote Sensing: A Review

2022-06-27 · Yi Wang, Conrad M Albrecht, Nassim Ait Ali Braham, Lichao Mou 외

In deep learning research, self-supervised learning (SSL) has received great attention triggering interest within both the computer vision and remote sensing communities. While there has been a big success in computer vi…

Earth ObservationImage ClassificationMulti-Label Image ClassificationSelf-Supervised Learning

USat: A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagery

2023-12-02 · Jeremy Irvin, Lucas Tao, Joanne Zhou, Yuntao Ma 외

Large, self-supervised vision models have led to substantial advancements for automatically interpreting natural images. Recent works have begun tailoring these methods to remote sensing data which has rich structure wit…