A Study on Differentiable Logic and LLMs for EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2023

TL;DR

This paper explores using differentiable logic and large language models to improve unsupervised domain adaptation for action recognition in videos, achieving top accuracy in the EPIC-KITCHENS-100 challenge.

Contribution

It introduces a novel differentiable logic loss combined with LLM-generated rules to enhance model adaptation to unseen action labels.

Findings

Moderate performance improvement with co-occurrence logic loss.

Using GPT-3.5 for rule generation slightly decreases performance.

Achieved first place in top-1 action recognition accuracy.

Abstract

In this technical report, we present our findings from a study conducted on the EPIC-KITCHENS-100 Unsupervised Domain Adaptation task for Action Recognition. Our research focuses on the innovative application of a differentiable logic loss in the training to leverage the co-occurrence relations between verb and noun, as well as the pre-trained Large Language Models (LLMs) to generate the logic rules for the adaptation to unseen action labels. Specifically, the model's predictions are treated as the truth assignment of a co-occurrence logic formula to compute the logic loss, which measures the consistency between the predictions and the logic constraints. By using the verb-noun co-occurrence matrix generated from the dataset, we observe a moderate improvement in model performance compared to our baseline framework. To further enhance the model's adaptability to novel action labels, we experiment with rules generated using GPT-3.5, which leads to a slight decrease in performance. These findings shed light on the potential and challenges of incorporating differentiable logic and LLMs for knowledge extraction in unsupervised domain adaptation for action recognition. Our final submission (entitled `NS-LLM') achieved the first place in terms of top-1 action recognition accuracy.