# Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment

arXiv: https://arxiv.org/abs/2004.03015 · HTML: https://mlsanity.com/paper/2004.03015/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2020.

## Built on by (most cited first, 28 of 28)

- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (2022)
- [VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining](https://mlsanity.com/paper/2303.14302/) (2023)
- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [Image Composition Assessment with Saliency-augmented Multi-pattern Pooling](https://mlsanity.com/paper/2104.03133/) (2021)
- [A Circular-Structured Representation for Visual Emotion Distribution Learning](https://mlsanity.com/paper/2106.12450/) (2021)
- [Understanding Aesthetics with Language: A Photo Critique Dataset for Aesthetic Assessment](https://mlsanity.com/paper/2206.08614/) (2022)
- [Quality Assessment for AI Generated Images with Instruction Tuning](https://mlsanity.com/paper/2405.07346/) (2024)
- [Distilling Knowledge from Object Classification to Aesthetics Assessment](https://mlsanity.com/paper/2206.00809/) (2022)
- [A Quality Index Metric and Method for Online Self-Assessment of Autonomous Vehicles Sensory Perception](https://mlsanity.com/paper/2203.02588/) (2022)
- [A Hypothesis for the Aesthetic Appreciation in Neural Networks](https://mlsanity.com/paper/2108.02646/) (2021)
- [Composition and Style Attributes Guided Image Aesthetic Assessment](https://mlsanity.com/paper/2111.04647/) (2021)
- [Charm: The Missing Piece in ViT fine-tuning for Image Aesthetic Assessment](https://mlsanity.com/paper/2504.02522/) (2025)
- [A Survey on Image Aesthetic Assessment](https://mlsanity.com/paper/2103.11616/) (2021)
- [MULLER: Multilayer Laplacian Resizer for Vision](https://mlsanity.com/paper/2304.02859/) (2023)
- [CLIP Brings Better Features to Visual Aesthetics Learners](https://mlsanity.com/paper/2307.15640/) (2023)
- [Image Aesthetics Assessment via Learnable Queries](https://mlsanity.com/paper/2309.02861/) (2023)
- [Series Photo Selection via Multi-view Graph Learning](https://mlsanity.com/paper/2203.09736/) (2022)
- [Modeling, Quantifying, and Predicting Subjectivity of Image Aesthetics](https://mlsanity.com/paper/2208.09666/) (2022)
- [An Experience-based Direct Generation approach to Automatic Image Cropping](https://mlsanity.com/paper/2212.14561/) (2022)
- [SeLiNet: Sentiment enriched Lightweight Network for Emotion Recognition in Images](https://mlsanity.com/paper/2307.02773/) (2023)
- [From Fragment to One Piece: A Survey on AI-Driven Graphic Design](https://mlsanity.com/paper/2503.18641/) (2025)
- [A Deep Drift-Diffusion Model for Image Aesthetic Score Distribution Prediction](https://mlsanity.com/paper/2010.07661/) (2020)
- [Exploring CNN-based models for image's aesthetic score prediction with using ensemble](https://mlsanity.com/paper/2210.05119/) (2022)
- [Multi-modal Learnable Queries for Image Aesthetics Assessment](https://mlsanity.com/paper/2405.01326/) (2024)
- [Considering user agreement in learning to predict the aesthetic quality](https://mlsanity.com/paper/2110.06956/) (2021)
- [Attributes-aware Visual Emotion Representation Learning](https://mlsanity.com/paper/2504.06578/) (2025)
- [Aesthetic Image Captioning with Saliency Enhanced MLLMs](https://mlsanity.com/paper/2509.04378/) (2025)

## Abstract (arXiv)

To leverage deep learning for image aesthetics assessment, one critical but unsolved issue is how to seamlessly incorporate the information of image aspect ratios to learn more robust models. In this paper, an adaptive fractional dilated convolution (AFDC), which is aspect-ratio-embedded, composition-preserving and parameter-free, is developed to tackle this issue natively in convolutional kernel level. Specifically, the fractional dilated kernel is adaptively constructed according to the image aspect ratios, where the interpolation of nearest two integers dilated kernels is used to cope with the misalignment of fractional sampling. Moreover, we provide a concise formulation for mini-batch training and utilize a grouping strategy to reduce computational overhead. As a result, it can be easily implemented by common deep learning libraries and plugged into popular CNN architectures in a computation-efficient manner. Our experimental results demonstrate that our proposed method achieves state-of-the-art performance on image aesthetics assessment over the AVA dataset.