• Corpus ID: 236924697

A Hypothesis for the Aesthetic Appreciation in Neural Networks

  title={A Hypothesis for the Aesthetic Appreciation in Neural Networks},
  author={Xu Cheng and Xin Wang and Hao Xue and Zhe Liang and Quanshi Zhang},
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… 

Figures from this paper

A Unified Game-Theoretic Interpretation of Adversarial Robustness

It is discovered that adversarial attacks mainly affect high-order interactions to fool the DNN, and the robustness of adversarially trained DNNs comes from category-specific low- order interactions.

Visualizing the Emergence of Intermediate Visual Patterns in DNNs

A method to visualize the discrimination power of intermediate-layer visual patterns encoded by a DNN and provides new insights into signal-processing behaviors of existing deep-learning techniques, such as adversarial attacks and knowledge distillation.



Neural Aesthetic Image Reviewer

This work proposes a model, referred to as Neural Aesthetic Image Reviewer, which can not only give an aesthetic score for an image, but also generate a textual description explaining why the image leads to a plausible rating score.

A model of aesthetic appreciation and aesthetic judgments.

It is explained why modern art's large number of individualized styles, innovativeness and conceptuality offer positive aesthetic experiences and why the challenge of art is mainly driven by a need for understanding.

Domain generality and domain specificity in aesthetic appreciation

Studying Aesthetics in Photographic Images Using a Computational Approach

This paper treats the challenge of automatically inferring aesthetic quality of pictures using their visual content as a machine learning problem, with a peer-rated online photo sharing Website as data source and extracts certain visual features based on the intuition that they can discriminate between aesthetically pleasing and displeasing images.

Revisiting Image Aesthetic Assessment via Self-Supervised Feature Learning

This paper designs two novel pretext tasks to identify the types and parameters of editing operations applied to synthetic instances and adapt them for a one-layer linear classifier to evaluate the performance in terms of binary aesthetic classification.

Joint Image and Text Representation for Aesthetics Analysis

Experimental results indicate that the proposed joint representation improves the performance of aesthetics assessment on the benchmarking AVA dataset, comparing with only visual features.

Image aesthetics assessment using Deep Chatterjee's machine

This work designs Deep Chatterjee's Machine (DCM), a model tailored for aesthetics assessment that extends to predicting the distribution of human ratings, and highlights a first-of-its-kind study of label-preserving transformations in the context of aesthetics assessment.

Aesthetic Critiques Generation for Photos

This work extends the image captioning task to produce captions related to photo aesthetics and/or photography skills and introduces a new dataset for aesthetics captioning called the Photo Critique Captioning Dataset (PCCD), which contains pair-wise image-comment data from professional photographers.

Photo Aesthetics Ranking Network with Attributes and Content Adaptation

This work proposes to learn a deep convolutional neural network to rank photo aesthetics in which the relative ranking of photo aesthetics are directly modeled in the loss function.