HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding

TL;DR

This paper introduces HERM-Bench, a new benchmark and dataset for evaluating and improving multimodal large language models' ability to understand human-centric scenarios, leading to a new model HERM-7B that outperforms existing models.

Contribution

The paper presents a novel benchmark, HERM-Bench, and a comprehensive dataset, HERM-100K, to enhance training and evaluation of MLLMs for human-centric understanding, along with a new model HERM-7B.

Findings

HERM-7B outperforms existing MLLMs on human-centric tasks.

Existing MLLMs have limitations in understanding complex human-centric scenarios.

Specialized datasets improve MLLMs' human-centric understanding.

Abstract

The significant advancements in visual understanding and instruction following from Multimodal Large Language Models (MLLMs) have opened up more possibilities for broader applications in diverse and universal human-centric scenarios. However, existing image-text data may not support the precise modality alignment and integration of multi-grained information, which is crucial for human-centric visual understanding. In this paper, we introduce HERM-Bench, a benchmark for evaluating the human-centric understanding capabilities of MLLMs. Our work reveals the limitations of existing MLLMs in understanding complex human-centric scenarios. To address these challenges, we present HERM-100K, a comprehensive dataset with multi-level human-centric annotations, aimed at enhancing MLLMs' training. Furthermore, we develop HERM-7B, a MLLM that leverages enhanced training data from HERM-100K. Evaluations on HERM-Bench demonstrate that HERM-7B significantly outperforms existing MLLMs across various human-centric dimensions, reflecting the current inadequacy of data annotations used in MLLM training for human-centric visual understanding. This research emphasizes the importance of specialized datasets and benchmarks in advancing the MLLMs' capabilities for human-centric understanding.