AI-Generated Lecture Slides for Improving Slide Element Detection and Retrieval
This work addresses the labor-intensive annotation bottleneck for slide understanding tasks, offering a synthetic data solution to enhance model training in educational or document analysis domains.
The paper tackles the problem of limited manual annotation for lecture slide element detection and retrieval by proposing an LLM-guided synthetic slide generation pipeline, SynLecSlideGen, and shows that few-shot transfer learning with pretraining on synthetic slides significantly improves performance compared to training only on real data.
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/.