mlsanityData to 7 Oct 2026

A Hypothesis for the Aesthetic Appreciation in Neural Networks

arXiv 2108.02646 ↗First posted 31 Jul 2021cs.LG cs.AI cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

This paper proposes a hypothesis for the aesthetic appreciation that aesthetic images make a neural network strengthen salient concepts and discard inessential concepts. In order to verify this hypothesis, we use multi-variate interactions to represent salient concepts and inessential concepts contained in images. Furthermore, we design a set of operations to revise images towards more beautiful ones. In experiments, we find that the revised images are more aesthetic than the original ones to some extent.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 19 of its 79 references that are in the map. First posted on arXiv 31 Jul 2021.

Builds on

19 of 79 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  4. 2015Holistically-Nested Edge Detectioncited by 590
  5. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  6. 2015LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancementcited by 224
  7. 2016Photo Aesthetics Ranking Network with Attributes and Content Adaptationcited by 122
  8. 2019Effective Aesthetics Prediction with Multi-level Spatially Pooled Featurescited by 52
  9. 2017Aesthetic-Driven Image Enhancement by Adversarial Learningcited by 38
  10. 2019Reliable and Efficient Image Cropping: A Grid Anchor based Approachcited by 32
  11. 2017A-Lamp: Adaptive Layout-Aware Multi-Patch Deep Convolutional Neural Network for Photo Aesthetic Assessmentcited by 28
  12. 2020Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessmentcited by 28
7 more
  1. 2019Image Cropping with Composition and Saliency Aware Aesthetic Score Mapcited by 20
  2. 2019Aesthetic Attributes Assessment of Imagescited by 18
  3. 2019Composition-Aware Image Aesthetics Assessmentcited by 15
  4. 2018Neural Aesthetic Image Reviewercited by 11
  5. 2015Automatic Content-Aware Color and Tone Stylizationcited by 7
  6. 2019Revisiting Image Aesthetic Assessment via Self-Supervised Feature Learningcited by 7
  7. 2016Fast-AT: Fast Automatic Thumbnail Generation using Deep Neural Networkscited by 6

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 0; 2023: 5; 2024: 1.

9 papers.

  1. 2021Defining and Quantifying the Emergence of Sparse Concepts in DNNscited by 36
  2. 2023Does a Neural Network Really Encode Symbolic Concepts?cited by 27
  3. 2023Explaining Generalization Power of a DNN Using Interactive Conceptscited by 25
  4. 2021A Unified Game-Theoretic Interpretation of Adversarial Robustnesscited by 17
  5. 2024Towards the Dynamics of a DNN Learning Symbolic Interactionscited by 13
  6. 2023Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?cited by 11
  7. 2023Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNscited by 10
  8. 2023Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Modelscited by 8
  9. 2021Visualizing the Emergence of Intermediate Visual Patterns in DNNscited by 7