# Image Composition Assessment with Saliency-augmented Multi-pattern Pooling

arXiv: https://arxiv.org/abs/2104.03133 · HTML: https://mlsanity.com/paper/2104.03133/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 68 references that are in the map.
- First posted on arXiv 7 Apr 2021.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [Deeply supervised salient object detection with short connections](https://mlsanity.com/paper/1611.04849/) (2016)
- [Pyramid Feature Attention Network for Saliency detection](https://mlsanity.com/paper/1903.00179/) (2019)
- [Photo Aesthetics Ranking Network with Attributes and Content Adaptation](https://mlsanity.com/paper/1606.01621/) (2016)
- [Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model](https://mlsanity.com/paper/1611.09571/) (2016)
- [Image Aesthetic Assessment: An Experimental Survey](https://mlsanity.com/paper/1610.00838/) (2016)
- [Squared Earth Mover's Distance-based Loss for Training Deep Neural Networks](https://mlsanity.com/paper/1611.05916/) (2016)
- [A-Lamp: Adaptive Layout-Aware Multi-Patch Deep Convolutional Neural Network for Photo Aesthetic Assessment](https://mlsanity.com/paper/1704.00248/) (2017)
- [Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment](https://mlsanity.com/paper/2004.03015/) (2020)
- [Learning to Compose with Professional Photographs on the Web](https://mlsanity.com/paper/1702.00503/) (2017)
- [Image Cropping with Composition and Saliency Aware Aesthetic Score Map](https://mlsanity.com/paper/1911.10492/) (2019)
- [Aesthetic Attributes Assessment of Images](https://mlsanity.com/paper/1907.04983/) (2019)
- [Composition-Aware Image Aesthetics Assessment](https://mlsanity.com/paper/1907.10801/) (2019)
- [Will People Like Your Image? Learning the Aesthetic Space](https://mlsanity.com/paper/1611.05203/) (2016)
- [Neural Aesthetic Image Reviewer](https://mlsanity.com/paper/1802.10240/) (2018)
- [Learning to Detect Multiple Photographic Defects](https://mlsanity.com/paper/1612.01635/) (2016)

## Built on by (most cited first, 21 of 21)

- [Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives](https://mlsanity.com/paper/2211.04894/) (2022)
- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approach](https://mlsanity.com/paper/2305.12726/) (2023)
- [DreamEdit: Subject-driven Image Editing](https://mlsanity.com/paper/2306.12624/) (2023)
- [Best Prompts for Text-to-Image Models and How to Find Them](https://mlsanity.com/paper/2209.11711/) (2022)
- [JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization](https://mlsanity.com/paper/2511.23002/) (2025)
- [X-IQE: eXplainable Image Quality Evaluation for Text-to-Image Generation with Visual Large Language Models](https://mlsanity.com/paper/2305.10843/) (2023)
- [PhotoFramer: Multi-modal Image Composition Instruction](https://mlsanity.com/paper/2512.00993/) (2025)
- [Finding Waldo: Towards Efficient Exploration of NeRF Scene Spaces](https://mlsanity.com/paper/2403.04508/) (2024)
- [Semantic to Structure: Learning Structural Representations for Infringement Detection](https://mlsanity.com/paper/2502.07323/) (2025)
- [Self-supervised Photographic Image Layout Representation Learning](https://mlsanity.com/paper/2403.03740/) (2024)
- [3D View Optimization for Improving Image Aesthetics](https://mlsanity.com/paper/2405.16443/) (2024)
- [AID-AppEAL: Automatic Image Dataset and Algorithm for Content Appeal Enhancement and Assessment Labeling](https://mlsanity.com/paper/2407.05546/) (2024)
- [Aesthetic Camera Viewpoint Suggestion with 3D Aesthetic Field](https://mlsanity.com/paper/2602.20363/) (2026)
- [CROP: Expert-Aligned Image Cropping via Compositional Reasoning and Optimizing Preference](https://mlsanity.com/paper/2605.12545/) (2026)
- [Explaining Automatic Image Assessment](https://mlsanity.com/paper/2502.01873/) (2025)
- [Semantically Stable Image Composition Analysis via Saliency and Gradient Vector Flow Fusion](https://mlsanity.com/paper/2604.16500/) (2026)
- [Progressive Photorealistic Simplification](https://mlsanity.com/paper/2605.10409/) (2026)
- [COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models](https://mlsanity.com/paper/2606.28696/) (2026)
- [Learning visual representations for compositional analysis of artworks and photographs](https://mlsanity.com/paper/2608.06142/) (2026)
- [Discrete Annotation, Continuous Preference: Rethinking Supervision for Accurate and Generalizable Aesthetic Image Cropping](https://mlsanity.com/paper/2610.00582/) (2026)

## Abstract (arXiv)

Image composition assessment is crucial in aesthetic assessment, which aims to assess the overall composition quality of a given image. However, to the best of our knowledge, there is neither dataset nor method specifically proposed for this task. In this paper, we contribute the first composition assessment dataset CADB with composition scores for each image provided by multiple professional raters. Besides, we propose a composition assessment network SAMP-Net with a novel Saliency-Augmented Multi-pattern Pooling (SAMP) module, which analyses visual layout from the perspectives of multiple composition patterns. We also leverage composition-relevant attributes to further boost the performance, and extend Earth Mover's Distance (EMD) loss to weighted EMD loss to eliminate the content bias. The experimental results show that our SAMP-Net can perform more favorably than previous aesthetic assessment approaches.