Towards Fine-Grained Recognition with Large Visual Language Models: Benchmark and Optimization Strategies

TL;DR

This paper introduces a new benchmark and optimization strategies for large vision-language models to enhance fine-grained recognition, addressing a gap in existing evaluation methods and demonstrating significant performance improvements.

Contribution

The paper presents the FROW benchmark for detailed evaluation of LVLMs and proposes data construction and training strategies to improve fine-grained recognition performance.

Findings

Mosaic data improves category recognition accuracy by 1%.

Open-world data boosts FROW accuracy by 10%-20%.

Fine-grained data in pre-training increases recognition accuracy by up to 10%.

Abstract

Large Vision Language Models (LVLMs) have made remarkable progress, enabling sophisticated vision-language interaction and dialogue applications. However, existing benchmarks primarily focus on reasoning tasks, often neglecting fine-grained recognition, which is crucial for practical application scenarios. To address this gap, we introduce the Fine-grained Recognition Open World (FROW) benchmark, designed for detailed evaluation of LVLMs with GPT-4o. On the basis of that, we propose a novel optimization strategy from two perspectives: \textit{data construction} and \textit{training process}, to improve the performance of LVLMs. Our dataset includes mosaic data, which combines multiple short-answer responses, and open-world data, generated from real-world questions and answers using GPT-4o, creating a comprehensive framework for evaluating fine-grained recognition in LVLMs. Experiments show that mosaic data improves category recognition accuracy by 1\% and open-world data boosts FROW benchmark accuracy by 10\%-20\% and content accuracy by 6\%-12\%. Meanwhile, incorporating fine-grained data into the pre-training phase can improve the model's category recognition accuracy by up to 10\%. The benchmark will be available at https://github.com/pc-inno/FROW.