Research Area:  Machine Learning

Abstract:

Domain-specific knowledge can significantly contribute to addressing a wide variety of vision tasks. However, the generation of such knowledge entails considerable human labor and time costs. This study investigates the potential of Large Language Models (LLMs) in generating and providing domain-specific information through semantic embeddings. To achieve this, an LLM is integrated into a pipeline that utilizes Knowledge Graphs and pre-trained semantic vectors in the context of the Vision-based Zero-shot Object State Classification task. We thoroughly examine the behavior of the LLM through an extensive ablation study. Our findings reveal that the integration of LLM-based embeddings, in combination with general-purpose pre-trained embeddings, leads to substantial performance improvements. Drawing insights from this ablation study, we conduct a comparative analysis against competing models, thereby highlighting the state-of-the-art performance achieved by the proposed approach.

Keywords:  

Author(s) Name:  Filippos Gouidis, Katerina Papantoniou, Konstantinos Papoutsakis, Theodore Patkos, Antonis Argyros, Dimitris Plexousakis

Publisher name:  arXiv

DOI:  10.48550/arXiv.2403.12151

Volume Information:  Volume 266, (2024)

Paper Link:   https://arxiv.org/abs/2403.12151