AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception
- URL: http://arxiv.org/abs/2404.09624v3
- Date: Wed, 24 Jul 2024 05:28:49 GMT
- Title: AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception
- Authors: Yipo Huang, Xiangfei Sheng, Zhichao Yang, Quan Yuan, Zhichao Duan, Pengfei Chen, Leida Li, Weisi Lin, Guangming Shi,
- Abstract summary: We develop a corpus-rich aesthetic critique database with 21,904 diverse-sourced images and 88K human natural language feedbacks.
We fine-tune the open-sourced general foundation models, achieving multi-modality Aesthetic Expert models, dubbed AesExpert.
Experiments demonstrate that the proposed AesExpert models deliver significantly better aesthetic perception performances than the state-of-the-art MLLMs.
- Score: 74.11069437400398
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The highly abstract nature of image aesthetics perception (IAP) poses significant challenge for current multimodal large language models (MLLMs). The lack of human-annotated multi-modality aesthetic data further exacerbates this dilemma, resulting in MLLMs falling short of aesthetics perception capabilities. To address the above challenge, we first introduce a comprehensively annotated Aesthetic Multi-Modality Instruction Tuning (AesMMIT) dataset, which serves as the footstone for building multi-modality aesthetics foundation models. Specifically, to align MLLMs with human aesthetics perception, we construct a corpus-rich aesthetic critique database with 21,904 diverse-sourced images and 88K human natural language feedbacks, which are collected via progressive questions, ranging from coarse-grained aesthetic grades to fine-grained aesthetic descriptions. To ensure that MLLMs can handle diverse queries, we further prompt GPT to refine the aesthetic critiques and assemble the large-scale aesthetic instruction tuning dataset, i.e. AesMMIT, which consists of 409K multi-typed instructions to activate stronger aesthetic capabilities. Based on the AesMMIT database, we fine-tune the open-sourced general foundation models, achieving multi-modality Aesthetic Expert models, dubbed AesExpert. Extensive experiments demonstrate that the proposed AesExpert models deliver significantly better aesthetic perception performances than the state-of-the-art MLLMs, including the most advanced GPT-4V and Gemini-Pro-Vision. Project homepage: https://yipoh.github.io/aes-expert/.
Related papers
- Multimodal LLMs Can Reason about Aesthetics in Zero-Shot [19.5597806965592]
We present the first study on how Multimodal LLMs' (MLLMs) reasoning ability shall be elicited to evaluate the aesthetics of artworks.
We develop a principled method for human preference modeling and perform a systematic correlation analysis between MLLMs' responses and human preference.
Our experiments reveal an inherent hallucination issue of MLLMs in art evaluation, associated with response subjectivity.
arXiv Detail & Related papers (2025-01-15T18:56:22Z) - Advancing Comprehensive Aesthetic Insight with Multi-Scale Text-Guided Self-Supervised Learning [14.405750888492735]
Image Aesthetic Assessment (IAA) is a vital and intricate task that entails analyzing and assessing an image's aesthetic values.
Traditional methods of IAA often concentrate on a single aesthetic task and suffer from inadequate labeled datasets.
We propose a comprehensive aesthetic MLLM capable of nuanced aesthetic insight.
arXiv Detail & Related papers (2024-12-16T16:35:35Z) - Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms [91.19304518033144]
We aim to align vision models with human aesthetic standards in a retrieval system.
We propose a preference-based reinforcement learning method that fine-tunes the vision models to better align the vision models with human aesthetics.
arXiv Detail & Related papers (2024-06-13T17:59:20Z) - NoteLLM-2: Multimodal Large Representation Models for Recommendation [71.87790090964734]
Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks.
Their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains underexplored.
We propose an end-to-end fine-tuning method that customizes the integration of any existing LLMs and vision encoders for efficient multimodal representation.
arXiv Detail & Related papers (2024-05-27T03:24:01Z) - AesBench: An Expert Benchmark for Multimodal Large Language Models on
Image Aesthetics Perception [64.25808552299905]
AesBench is an expert benchmark aiming to comprehensively evaluate the aesthetic perception capacities of MLLMs.
We construct an Expert-labeled Aesthetics Perception Database (EAPD), which features diversified image contents and high-quality annotations provided by professional aesthetic experts.
We propose a set of integrative criteria to measure the aesthetic perception abilities of MLLMs from four perspectives, including Perception (AesP), Empathy (AesE), Assessment (AesA) and Interpretation (AesI)
arXiv Detail & Related papers (2024-01-16T10:58:07Z) - Unveiling The Factors of Aesthetic Preferences with Explainable AI [0.0]
In this study, we pioneer a novel perspective by utilizing several different machine learning (ML) models.
Our models process these attributes as inputs to predict the aesthetic scores of images.
Our aim is to shed light on the complex nature of aesthetic preferences in images through ML and to provide a deeper understanding of the attributes that influence aesthetic judgements.
arXiv Detail & Related papers (2023-11-24T11:06:22Z) - Q-Instruct: Improving Low-level Visual Abilities for Multi-modality
Foundation Models [81.20804369985376]
We conduct a large-scale subjective experiment collecting a vast number of real human feedbacks on low-level vision.
The constructed **Q-Pathway** dataset includes 58K detailed human feedbacks on 18,973 images.
We design a GPT-participated conversion to process these feedbacks into diverse-format 200K instruction-response pairs.
arXiv Detail & Related papers (2023-11-12T09:10:51Z) - VILA: Learning Image Aesthetics from User Comments with Vision-Language
Pretraining [53.470662123170555]
We propose learning image aesthetics from user comments, and exploring vision-language pretraining methods to learn multimodal aesthetic representations.
Specifically, we pretrain an image-text encoder-decoder model with image-comment pairs, using contrastive and generative objectives to learn rich and generic aesthetic semantics without human labels.
Our results show that our pretrained aesthetic vision-language model outperforms prior works on image aesthetic captioning over the AVA-Captions dataset.
arXiv Detail & Related papers (2023-03-24T23:57:28Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.