Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms

• URL: http://arxiv.org/abs/2406.09397v1
• Date: Thu, 13 Jun 2024 17:59:20 GMT
• Title: Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms
• Authors: Miaosen Zhang, Yixuan Wei, Zhen Xing, Yifei Ma, Zuxuan Wu, Ji Li, Zheng Zhang, Qi Dai, Chong Luo, Xin Geng, Baining Guo,
• Abstract summary: 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.
• Score: 91.19304518033144
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern vision models are trained on very large noisy datasets. While these models acquire strong capabilities, they may not follow the user's intent to output the desired results in certain aspects, e.g., visual aesthetic, preferred style, and responsibility. In this paper, we target the realm of visual aesthetics and aim to align vision models with human aesthetic standards in a retrieval system. Advanced retrieval systems usually adopt a cascade of aesthetic models as re-rankers or filters, which are limited to low-level features like saturation and perform poorly when stylistic, cultural or knowledge contexts are involved. We find that utilizing the reasoning ability of large language models (LLMs) to rephrase the search query and extend the aesthetic expectations can make up for this shortcoming. Based on the above findings, we propose a preference-based reinforcement learning method that fine-tunes the vision models to distill the knowledge from both LLMs reasoning and the aesthetic models to better align the vision models with human aesthetics. Meanwhile, with rare benchmarks designed for evaluating retrieval systems, we leverage large multi-modality model (LMM) to evaluate the aesthetic performance with their strong abilities. As aesthetic assessment is one of the most subjective tasks, to validate the robustness of LMM, we further propose a novel dataset named HPIR to benchmark the alignment with human aesthetics. Experiments demonstrate that our method significantly enhances the aesthetic behaviors of the vision models, under several metrics. We believe the proposed algorithm can be a general practice for aligning vision models with human values.

Related papers

• From Efficiency to Equity: Measuring Fairness in Preference Learning [3.2132738637761027]
  We evaluate fairness in preference learning models inspired by economic theories of inequality and Rawlsian justice. We propose metrics adapted from the Gini Coefficient, Atkinson Index, and Kuznets Ratio to quantify fairness in these models.
  arXiv  Detail & Related papers  (2024-10-24T15:25:56Z)
• VHELM: A Holistic Evaluation of Vision Language Models [75.88987277686914]
  We present the Holistic Evaluation of Vision Language Models (VHELM) VHELM aggregates various datasets to cover one or more of the 9 aspects: visual perception, knowledge, reasoning, bias, fairness, multilinguality, robustness, toxicity, and safety. Our framework is designed to be lightweight and automatic so that evaluation runs are cheap and fast.
  arXiv  Detail & Related papers  (2024-10-09T17:46:34Z)
• Benchmarks as Microscopes: A Call for Model Metrology [76.64402390208576]
  Modern language models (LMs) pose a new challenge in capability assessment. To be confident in our metrics, we need a new discipline of model metrology.
  arXiv  Detail & Related papers  (2024-07-22T17:52:12Z)
• Data-efficient Large Vision Models through Sequential Autoregression [58.26179273091461]
  We develop an efficient, autoregression-based vision model on a limited dataset. We demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint.
  arXiv  Detail & Related papers  (2024-02-07T13:41:53Z)
• 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)
• InDL: A New Dataset and Benchmark for In-Diagram Logic Interpretation based on Visual Illusion [1.7980584146314789]
  This paper introduces a novel approach to evaluating deep learning models' capacity for in-diagram logic interpretation. We establish a unique dataset, InDL, designed to rigorously test and benchmark these models. We utilize six classic geometric optical illusions to create a comparative framework between human and machine visual perception.
  arXiv  Detail & Related papers  (2023-05-28T13:01:32Z)
• ALL-E: Aesthetics-guided Low-light Image Enhancement [45.40896781156727]
  We propose a new paradigm, i.e. aesthetics-guided low-light image enhancement (ALL-E) It introduces aesthetic preferences to LLE and motivates training in a reinforcement learning framework with an aesthetic reward. Our results on various benchmarks demonstrate the superiority of ALL-E over state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-04-28T03:34:10Z)
• 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)
• Image Quality Assessment in the Modern Age [53.19271326110551]
  This tutorial provides the audience with the basic theories, methodologies, and current progresses of image quality assessment (IQA) We will first revisit several subjective quality assessment methodologies, with emphasis on how to properly select visual stimuli. Both hand-engineered and (deep) learning-based methods will be covered.
  arXiv  Detail & Related papers  (2021-10-19T02:38:46Z)
• Who Explains the Explanation? Quantitatively Assessing Feature Attribution Methods [0.0]
  We propose a novel evaluation metric -- the Focus -- designed to quantify the faithfulness of explanations. We show the robustness of the metric through randomization experiments, and then use Focus to evaluate and compare three popular explainability techniques. Our results find LRP and GradCAM to be consistent and reliable, while the latter remains most competitive even when applied to poorly performing models.
  arXiv  Detail & Related papers  (2021-09-28T07:10:24Z)

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.