# Distilling Knowledge from Object Classification to Aesthetics Assessment

arXiv: https://arxiv.org/abs/2206.00809 · HTML: https://mlsanity.com/paper/2206.00809/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 52 references that are in the map.
- First posted on arXiv 2 Jun 2022.

## Builds on (most cited first, 20 of 20)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [Billion-scale semi-supervised learning for image classification](https://mlsanity.com/paper/1905.00546/) (2019)
- [Knowledge Adaptation for Efficient Semantic Segmentation](https://mlsanity.com/paper/1903.04688/) (2019)
- [Inter-Region Affinity Distillation for Road Marking Segmentation](https://mlsanity.com/paper/2004.05304/) (2020)
- [Effective Aesthetics Prediction with Multi-level Spatially Pooled Features](https://mlsanity.com/paper/1904.01382/) (2019)
- [Learning to Resize Images for Computer Vision Tasks](https://mlsanity.com/paper/2103.09950/) (2021)
- [Complementary Relation Contrastive Distillation](https://mlsanity.com/paper/2103.16367/) (2021)
- [Continual Learning for Blind Image Quality Assessment](https://mlsanity.com/paper/2102.09717/) (2021)
- [Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment](https://mlsanity.com/paper/2004.03015/) (2020)
- [Aesthetic Attributes Assessment of Images](https://mlsanity.com/paper/1907.04983/) (2019)
- [A Gated Peripheral-Foveal Convolutional Neural Network for Unified Image Aesthetic Prediction](https://mlsanity.com/paper/1812.07989/) (2018)
- [A deep architecture for unified aesthetic prediction](https://mlsanity.com/paper/1708.04890/) (2017)

## Built on by (most cited first, 12 of 12)

- [Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives](https://mlsanity.com/paper/2211.04894/) (2022)
- [TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment](https://mlsanity.com/paper/2308.03060/) (2023)
- [Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approach](https://mlsanity.com/paper/2305.12726/) (2023)
- [UNIAA: A Unified Multi-modal Image Aesthetic Assessment Baseline and Benchmark](https://mlsanity.com/paper/2404.09619/) (2024)
- [DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment](https://mlsanity.com/paper/2206.09853/) (2022)
- [UniQA: Unified Vision-Language Pre-training for Image Quality and Aesthetic Assessment](https://mlsanity.com/paper/2406.01069/) (2024)
- [Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentation](https://mlsanity.com/paper/2303.13724/) (2023)
- [CRCNet: Few-shot Segmentation with Cross-Reference and Region-Global Conditional Networks](https://mlsanity.com/paper/2208.10761/) (2022)
- [Integrating Large Pre-trained Models into Multimodal Named Entity Recognition with Evidential Fusion](https://mlsanity.com/paper/2306.16991/) (2023)
- [CLIP Brings Better Features to Visual Aesthetics Learners](https://mlsanity.com/paper/2307.15640/) (2023)
- [Multi-modal Learnable Queries for Image Aesthetics Assessment](https://mlsanity.com/paper/2405.01326/) (2024)
- [Beyond Fidelity: Semantic Similarity Assessment in Low-Level Image Processing](https://mlsanity.com/paper/2604.25408/) (2026)

## Abstract (arXiv)

In this work, we point out that the major dilemma of image aesthetics assessment (IAA) comes from the abstract nature of aesthetic labels. That is, a vast variety of distinct contents can correspond to the same aesthetic label. On the one hand, during inference, the IAA model is required to relate various distinct contents to the same aesthetic label. On the other hand, when training, it would be hard for the IAA model to learn to distinguish different contents merely with the supervision from aesthetic labels, since aesthetic labels are not directly related to any specific content. To deal with this dilemma, we propose to distill knowledge on semantic patterns for a vast variety of image contents from multiple pre-trained object classification (POC) models to an IAA model. Expecting the combination of multiple POC models can provide sufficient knowledge on various image contents, the IAA model can easier learn to relate various distinct contents to a limited number of aesthetic labels. By supervising an end-to-end single-backbone IAA model with the distilled knowledge, the performance of the IAA model is significantly improved by 4.8% in SRCC compared to the version trained only with ground-truth aesthetic labels. On specific categories of images, the SRCC improvement brought by the proposed method can achieve up to 7.2%. Peer comparison also shows that our method outperforms 10 previous IAA methods.