English

VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining

Computer Vision and Pattern Recognition 2023-06-06 v2

Abstract

Assessing the aesthetics of an image is challenging, as it is influenced by multiple factors including composition, color, style, and high-level semantics. Existing image aesthetic assessment (IAA) methods primarily rely on human-labeled rating scores, which oversimplify the visual aesthetic information that humans perceive. Conversely, user comments offer more comprehensive information and are a more natural way to express human opinions and preferences regarding image aesthetics. In light of this, 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. To efficiently adapt the pretrained model for downstream IAA tasks, we further propose a lightweight rank-based adapter that employs text as an anchor to learn the aesthetic ranking concept. Our results show that our pretrained aesthetic vision-language model outperforms prior works on image aesthetic captioning over the AVA-Captions dataset, and it has powerful zero-shot capability for aesthetic tasks such as zero-shot style classification and zero-shot IAA, surpassing many supervised baselines. With only minimal finetuning parameters using the proposed adapter module, our model achieves state-of-the-art IAA performance over the AVA dataset.

Keywords

Cite

@article{arxiv.2303.14302,
  title  = {VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining},
  author = {Junjie Ke and Keren Ye and Jiahui Yu and Yonghui Wu and Peyman Milanfar and Feng Yang},
  journal= {arXiv preprint arXiv:2303.14302},
  year   = {2023}
}

Comments

CVPR 2023, https://github.com/google-research/google-research/tree/master/vila

R2 v1 2026-06-28T09:33:02.902Z