Advancing Comprehensive Aesthetic Insight with Multi-Scale Text-Guided Self-Supervised Learning
This work addresses the challenge of in-depth aesthetic comprehension for image analysis applications, though it appears incremental as it builds on existing MLLM approaches for a specific domain.
The paper tackled the problem of limited labeled data and single-task focus in Image Aesthetic Assessment (IAA) by proposing a comprehensive aesthetic Multi-modal Large Language Model (MLLM) with a multi-scale text-guided self-supervised learning technique, achieving new state-of-the-art benchmarks in tasks like aesthetic scoring, commenting, and personalized assessment, and demonstrating zero-shot learning in aesthetic suggesting.
Image Aesthetic Assessment (IAA) is a vital and intricate task that entails analyzing and assessing an image's aesthetic values, and identifying its highlights and areas for improvement. Traditional methods of IAA often concentrate on a single aesthetic task and suffer from inadequate labeled datasets, thus impairing in-depth aesthetic comprehension. Despite efforts to overcome this challenge through the application of Multi-modal Large Language Models (MLLMs), such models remain underdeveloped for IAA purposes. To address this, we propose a comprehensive aesthetic MLLM capable of nuanced aesthetic insight. Central to our approach is an innovative multi-scale text-guided self-supervised learning technique. This technique features a multi-scale feature alignment module and capitalizes on a wealth of unlabeled data in a self-supervised manner to structurally and functionally enhance aesthetic ability. The empirical evidence indicates that accompanied with extensive instruct-tuning, our model sets new state-of-the-art benchmarks across multiple tasks, including aesthetic scoring, aesthetic commenting, and personalized image aesthetic assessment. Remarkably, it also demonstrates zero-shot learning capabilities in the emerging task of aesthetic suggesting. Furthermore, for personalized image aesthetic assessment, we harness the potential of in-context learning and showcase its inherent advantages.