mlsanityData to 14 Oct 2026

Scaling Up Personalized Image Aesthetic Assessment via Task Vector Customization

arXiv 2407.07176 ↗First posted 9 Jul 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

The task of personalized image aesthetic assessment seeks to tailor aesthetic score prediction models to match individual preferences with just a few user-provided inputs. However, the scalability and generalization capabilities of current approaches are considerably restricted by their reliance on an expensive curated database. To overcome this long-standing scalability challenge, we present a unique approach that leverages readily available databases for general image aesthetic assessment and image quality assessment. Specifically, we view each database as a distinct image score regression task that exhibits varying degrees of personalization potential. By determining optimal combinations of task vectors, known to represent specific traits of each database, we successfully create personalized models for individuals. This approach of integrating multiple models allows us to harness a substantial amount of data. Our extensive experiments demonstrate the effectiveness of our approach in generalizing to previously unseen domains-a challenge previous approaches have struggled to achieve-making it highly applicable to real-world scenarios. Our novel approach significantly advances the field by offering scalable solutions for personalized aesthetic assessment and establishing high standards for future research. https://yeolj00.github.io/personal-projects/personalized-aesthetics/

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 32 of its 56 references that are in the map. First posted on arXiv 9 Jul 2024.

Builds on

32 of 56 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  6. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,396
  7. 2022Editing Models with Task Arithmeticcited by 1,120
  8. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  9. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  10. 2021Robust fine-tuning of zero-shot modelscited by 797
  11. 2023DataComp: In search of the next generation of multimodal datasetscited by 644
  12. 2020Transformer Interpretability Beyond Attention Visualizationcited by 627
20 more
  1. 2021Intriguing Properties of Vision Transformerscited by 446
  2. 2017NIMA: Neural Image Assessmentcited by 389
  3. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 355
  4. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 302
  5. 2021Post-Training Quantization for Vision Transformercited by 278
  6. 2019From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Qualitycited by 223
  7. 2015Massive Online Crowdsourced Study of Subjective and Objective Picture Qualitycited by 209
  8. 2021PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationcited by 179
  9. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformercited by 151
  10. 2020MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessmentcited by 144
  11. 2016Photo Aesthetics Ranking Network with Attributes and Content Adaptationcited by 125
  12. 2023End-to-End Diffusion Latent Optimization Improves Classifier Guidancecited by 108
  13. 2023VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretrainingcited by 65
  14. 2022Personalized Image Aesthetics Assessment with Rich Attributescited by 58
  15. 2019Effective Aesthetics Prediction with Multi-level Spatially Pooled Featurescited by 53
  16. 2019Aesthetic Attributes Assessment of Imagescited by 18
  17. 2021On Data Efficiency of Meta-learningcited by 16
  18. 2021User-Guided Personalized Image Aesthetic Assessment based on Deep Reinforcement Learningcited by 7
  19. 2018USAR: an Interactive User-specific Aesthetic Ranking Framework for Imagescited by 5
  20. 2023CLIP Brings Better Features to Visual Aesthetics Learnerscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understandingcited by 41
  2. 2025Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Modelcited by 12
  3. 2025DesignPref: Capturing Personal Preferences in Visual Design Generationcited by 7
  4. 2025On the Role of Individual Differences in Current Approaches to Computational Image Aestheticscited by 1
  5. 2026Personalized Image Aesthetic Assessment via Preference-rich Sample Mining and Cohort Mergingcited by 1
  6. 2026Learning Color Grading, No Photo Sharing: Federated Aesthetic Preference Learning for Personalized Image Enhancementcited by 1