PainFormer: a Vision Foundation Model for Automatic Pain Assessment

TL;DR

PainFormer is a versatile vision foundation model trained on diverse datasets to automatically assess pain from multiple modalities, achieving state-of-the-art results and enabling continuous pain monitoring.

Contribution

Introduces PainFormer, a multi-task vision foundation model trained on 14 datasets with 10.9 million samples for automatic pain assessment across various modalities.

Findings

Effective extraction of high-quality embeddings from diverse modalities.

Achieves state-of-the-art performance on BioVid and AI4Pain datasets.

Demonstrates strong results in both unimodal and multimodal settings.

Abstract

Pain is a manifold condition that impacts a significant percentage of the population. Accurate and reliable pain evaluation for the people suffering is crucial to developing effective and advanced pain management protocols. Automatic pain assessment systems provide continuous monitoring and support decision-making processes, ultimately aiming to alleviate distress and prevent functionality decline. This study introduces PainFormer, a vision foundation model based on multi-task learning principles trained simultaneously on 14 tasks/datasets with a total of 10.9 million samples. Functioning as an embedding extractor for various input modalities, the foundation model provides feature representations to the Embedding-Mixer, a transformer-based module that performs the final pain assessment. Extensive experiments employing behavioral modalities - including RGB, synthetic thermal, and estimated depth videos - and physiological modalities such as ECG, EMG, GSR, and fNIRS revealed that PainFormer effectively extracts high-quality embeddings from diverse input modalities. The proposed framework is evaluated on two pain datasets, BioVid and AI4Pain, and directly compared to 75 different methodologies documented in the literature. Experiments conducted in unimodal and multimodal settings demonstrate state-of-the-art performances across modalities and pave the way toward general-purpose models for automatic pain assessment. The foundation model's architecture (code) and weights are available at: https://github.com/GkikasStefanos/PainFormer.