Lecture slide element detection and retrieval are key problems in slide understanding. Training effective models for these tasks often depends on extensive manual annotation. However, annotating large volumes of lecture slides for supervised training is labor intensive and requires domain expertise. To address this, we propose a large language model (LLM)-guided synthetic lecture slide generation pipeline, SynLecSlideGen, which produces high-quality, coherent and realistic slides. We also create an evaluation benchmark, namely RealSlide by manually annotating 1,050 real lecture slides. To assess the utility of our synthetic slides, we perform few-shot transfer learning on real data using models pre-trained on them. Experimental results show that few-shot transfer learning with pretraining on synthetic slides significantly improves performance compared to training only on real data. This demonstrates that synthetic data can effectively compensate for limited labeled lecture slides. The code and resources of our work are publicly available on our project website: https://synslidegen.github.io/.
@article{arxiv.2506.23605,
title = {AI-Generated Lecture Slides for Improving Slide Element Detection and Retrieval},
author = {Suyash Maniyar and Vishvesh Trivedi and Ajoy Mondal and Anand Mishra and C. V. Jawahar},
journal= {arXiv preprint arXiv:2506.23605},
year = {2025}
}
Comments
40 pages including supplementary, accepted at ICDAR 2025