Transductive Aesthetic Preference Propagation for Personalized Image Aesthetics Assessment

Li, Yaohui; Yang, Yuzhe; Li, Huaxiong; Chen, Haoxing; Xu, Liwu; Li, Leida; Li, Yaqian; Guo, Yandong

doi:10.1145/3503161.3548244

Cited by 8 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this kind of task, the personalized aesthetics models are optimized to quickly adapt to a new user's aesthetic preference, and these PIAA models may fail to capture personalized aesthetics [52]. To this end, recent PIAA works [23,44,49,52] based on metalearning paradigms are proposed to tackle this problem. Although the promising PIAA performance is achieved, most methods still have complex training frameworks [21,44,52] that are not suitable for deployment in practice.…”

Section: Related Workmentioning

confidence: 99%

MetaFBP: Learning to Learn High-Order Predictor for Personalized Facial Beauty Prediction

Lin,

Shen,

Yin

et al. 2023

Proceedings of the 31st ACM International Conference on Multimedia

View full text Add to dashboard Cite

Predicting individual aesthetic preferences holds significant practical applications and academic implications for human society. However, existing studies mainly focus on learning and predicting the commonality of facial attractiveness, with little attention given to Personalized Facial Beauty Prediction (PFBP). PFBP aims to develop a machine that can adapt to individual aesthetic preferences with only a few images rated by each user. In this paper, we formulate this task from a meta-learning perspective that each user corresponds to a meta-task. To address such PFBP task, we draw inspiration from the human aesthetic mechanism that visual aesthetics in society follows a Gaussian distribution, which motivates us to disentangle user preferences into a commonality and an individuality part. To this end, we propose a novel MetaFBP framework, in which we devise a universal feature extractor to capture the aesthetic commonality and then optimize to adapt the aesthetic individuality by shifting the decision boundary of the predictor via a meta-learning mechanism. Unlike conventional meta-learning methods that may struggle with slow adaptation or overfitting to tiny support sets, we propose a novel approach that optimizes a high-order predictor for fast adaptation. In order to validate the performance of the proposed method, we build several PFBP benchmarks by using existing facial beauty prediction datasets rated by numerous users. Extensive experiments on these benchmarks demonstrate the effectiveness of the proposed MetaFBP method.

show abstract

Section: Related Workmentioning

confidence: 99%

MetaFBP: Learning to Learn High-Order Predictor for Personalized Facial Beauty Prediction

Lin,

Shen,

Yin

et al. 2023

Proceedings of the 31st ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…Dynamic networks [3,8,12,17,33] focus on improving the representation ability of the deep models, which adapt the model structures or parameters during inferences. Essentially, dynamic models adaptively apply different weights on parameters or features of the models conditioned on inputs, which increases the model capacity and representation ability.…”

Section: Dynamics In Computer Visionmentioning

confidence: 99%

Hierarchical Dynamic Image Harmonization

Chen¹,

Gu²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Image harmonization is a critical task in computer vision, which aims to adjust the fore-ground to make it compatible with the back-ground. Recent works mainly focus on using global transformation (i.e., normalization and color curve rendering) to achieve visual consistency. However, these model ignore local consistency and their model size limit their harmonization ability on edge devices. Inspired by the dynamic deep networks that adapt the model structures or parameters conditioned on the inputs, we propose a hierarchical dynamic network (HDNet) for efficient image harmonization to adapt the model parameters and features from local to global view for better feature transformation. Specifically, local dynamics (LD) and mask-aware global dynamics (MGD) are applied. LD enables features of different channels and positions to change adaptively and improve the representation ability of geometric transformation through structural information learning. MGD learns the representations of fore-and back-ground regions and correlations to global harmonization. Experiments show that the proposed HDNet reduces more than 80% parameters compared with previous methods but still achieves the state-of-the-art performance on the popular iHarmony4 dataset. Our code is avaliable in https://github. com/chenhaoxing/HDNet.

show abstract

Hybrid CNN-transformer based meta-learning approach for personalized image aesthetics assessment

Yan,

Shao,

Chen

et al. 2024

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

Transductive Aesthetic Preference Propagation for Personalized Image Aesthetics Assessment

Cited by 8 publications

References 23 publications

MetaFBP: Learning to Learn High-Order Predictor for Personalized Facial Beauty Prediction

MetaFBP: Learning to Learn High-Order Predictor for Personalized Facial Beauty Prediction

Hierarchical Dynamic Image Harmonization

Hybrid CNN-transformer based meta-learning approach for personalized image aesthetics assessment

Contact Info

Product

Resources

About