Aesthetic Attribute Assessment of Images Numerically on Mixed Multi-attribute Datasets

• URL: http://arxiv.org/abs/2207.01806v1
• Date: Tue, 5 Jul 2022 04:42:10 GMT
• Title: Aesthetic Attribute Assessment of Images Numerically on Mixed Multi-attribute Datasets
• Authors: Xin Jin, Xinning Li, Hao Lou, Chenyu Fan, Qiang Deng, Chaoen Xiao, Shuai Cui, Amit Kumar Singh
• Abstract summary: We construct an image attribute dataset called aesthetic mixed dataset with attributes(AMD-A) and design external attribute features for fusion. Our model can achieve aesthetic classification, overall scoring and attribute scoring. Experimental results, using the MindSpore, show that our proposed method can effectively improve the performance of the aesthetic overall and attribute assessment.
• Score: 16.120684660965978
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the continuous development of social software and multimedia technology, images have become a kind of important carrier for spreading information and socializing. How to evaluate an image comprehensively has become the focus of recent researches. The traditional image aesthetic assessment methods often adopt single numerical overall assessment scores, which has certain subjectivity and can no longer meet the higher aesthetic requirements. In this paper, we construct an new image attribute dataset called aesthetic mixed dataset with attributes(AMD-A) and design external attribute features for fusion. Besides, we propose a efficient method for image aesthetic attribute assessment on mixed multi-attribute dataset and construct a multitasking network architecture by using the EfficientNet-B0 as the backbone network. Our model can achieve aesthetic classification, overall scoring and attribute scoring. In each sub-network, we improve the feature extraction through ECA channel attention module. As for the final overall scoring, we adopt the idea of the teacher-student network and use the classification sub-network to guide the aesthetic overall fine-grain regression. Experimental results, using the MindSpore, show that our proposed method can effectively improve the performance of the aesthetic overall and attribute assessment.

Related papers

• Predicting Scores of Various Aesthetic Attribute Sets by Learning from Overall Score Labels [54.63611854474985]
  In this paper, we propose to replace image attribute labels with feature extractors. We use networks from different tasks to provide attribute features to our F2S model. Our method makes it feasible to learn meaningful attribute scores for various aesthetic attribute sets in different types of images with only overall aesthetic scores.
  arXiv  Detail & Related papers  (2023-12-06T01:41:49Z)
• UMAAF: Unveiling Aesthetics via Multifarious Attributes of Images [16.647573404422175]
  We propose the Unified Multi-attribute Aesthetic Assessment Framework (UMAAF) to model both absolute and relative attributes of images. UMAAF achieves state-of-the-art performance on TAD66K and AVA datasets.
  arXiv  Detail & Related papers  (2023-11-19T11:57:01Z)
• Multi-task convolutional neural network for image aesthetic assessment [0.0]
  We present a multi-task convolutional neural network that takes into account aesthetic attributes. The proposed neural network jointly learns the attributes along with the overall aesthetic scores of images. We achieve near-human performance in terms of overall aesthetic scores when considering the Spearman's rank correlations.
  arXiv  Detail & Related papers  (2023-05-16T11:56:02Z)
• 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)
• Attribute Prototype Network for Any-Shot Learning [113.50220968583353]
  We argue that an image representation with integrated attribute localization ability would be beneficial for any-shot, i.e. zero-shot and few-shot, image classification tasks. We propose a novel representation learning framework that jointly learns global and local features using only class-level attributes.
  arXiv  Detail & Related papers  (2022-04-04T02:25:40Z)
• Composition and Style Attributes Guided Image Aesthetic Assessment [66.60253358722538]
  We propose a method for the automatic prediction of the aesthetics of an image. The proposed network includes: a pre-trained network for semantic features extraction (the Backbone); a Multi Layer Perceptron (MLP) network that relies on the Backbone features for the prediction of image attributes (the AttributeNet) Given an image, the proposed multi-network is able to predict: style and composition attributes, and aesthetic score distribution.
  arXiv  Detail & Related papers  (2021-11-08T17:16:38Z)
• Combining Image Features and Patient Metadata to Enhance Transfer Learning [0.0]
  We compare the performance of six state-of-the-art deep neural networks in classification tasks when using only image features, to when these are combined with patient metadata. Our results indicate that this performance enhancement may be a general property of deep networks and should be explored in other areas.
  arXiv  Detail & Related papers  (2021-10-08T15:43:31Z)
• Learning to Infer Unseen Attribute-Object Compositions [55.58107964602103]
  A graph-based model is proposed that can flexibly recognize both single- and multi-attribute-object compositions. We build a large-scale Multi-Attribute dataset with 116,099 images and 8,030 composition categories.
  arXiv  Detail & Related papers  (2020-10-27T14:57:35Z)
• Saliency-driven Class Impressions for Feature Visualization of Deep Neural Networks [55.11806035788036]
  It is advantageous to visualize the features considered to be essential for classification. Existing visualization methods develop high confidence images consisting of both background and foreground features. In this work, we propose a saliency-driven approach to visualize discriminative features that are considered most important for a given task.
  arXiv  Detail & Related papers  (2020-07-31T06:11:06Z)

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.