# DeepFL-IQA: Weak Supervision for Deep IQA Feature Learning

arXiv: https://arxiv.org/abs/2001.08113 · HTML: https://mlsanity.com/paper/2001.08113/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jan 2020.

## Built on by (most cited first, 29 of 29)

- [Image Quality Assessment using Contrastive Learning](https://mlsanity.com/paper/2110.13266/) (2021)
- [Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Dataset](https://mlsanity.com/paper/2405.18842/) (2024)
- [PyTorch Image Quality: Metrics for Image Quality Assessment](https://mlsanity.com/paper/2208.14818/) (2022)
- [2AFC Prompting of Large Multimodal Models for Image Quality Assessment](https://mlsanity.com/paper/2402.01162/) (2024)
- [Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessment](https://mlsanity.com/paper/2411.17237/) (2024)
- [Composition and Style Attributes Guided Image Aesthetic Assessment](https://mlsanity.com/paper/2111.04647/) (2021)
- [KonX: Cross-Resolution Image Quality Assessment](https://mlsanity.com/paper/2212.05813/) (2022)
- [Generalizable Video Quality Assessment via Weak-to-Strong Learning](https://mlsanity.com/paper/2505.03631/) (2025)
- [Vision Language Modeling of Content, Distortion and Appearance for Image Quality Assessment](https://mlsanity.com/paper/2406.09858/) (2024)
- [Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration](https://mlsanity.com/paper/2603.26385/) (2026)
- [VTAMIQ: Transformers for Attention Modulated Image Quality Assessment](https://mlsanity.com/paper/2110.01655/) (2021)
- [The First Comprehensive Dataset with Multiple Distortion Types for Visual Just-Noticeable Differences](https://mlsanity.com/paper/2303.02562/) (2023)
- [Collaborative Auto-encoding for Blind Image Quality Assessment](https://mlsanity.com/paper/2305.14684/) (2023)
- [Cross-Dataset-Robust Method for Blind Real-World Image Quality Assessment](https://mlsanity.com/paper/2309.14868/) (2023)
- [Joint Quality Assessment and Example-Guided Image Processing by Disentangling Picture Appearance from Content](https://mlsanity.com/paper/2404.13484/) (2024)
- [Adapting Pretrained Networks for Image Quality Assessment on High Dynamic Range Displays](https://mlsanity.com/paper/2405.00670/) (2024)
- [Enhanced Dermatology Image Quality Assessment via Cross-Domain Training](https://mlsanity.com/paper/2506.16116/) (2025)
- [HiRQA: Hierarchical Ranking and Quality Alignment for Opinion-Unaware Image Quality Assessment](https://mlsanity.com/paper/2508.15130/) (2025)
- [Revisiting Vision Language Foundations for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2509.17374/) (2025)
- [ExIQA: Explainable Image Quality Assessment Using Distortion Attributes](https://mlsanity.com/paper/2409.06853/) (2024)
- [Image Quality Assessment: Exploring Regional Heterogeneity via Response of Adaptive Multiple Quality Factors in Dictionary Space](https://mlsanity.com/paper/2412.18160/) (2024)
- [BELE: Blur Equivalent Linearized Estimator](https://mlsanity.com/paper/2503.00503/) (2025)
- [Language Integration in Fine-Tuning Multimodal Large Language Models for Image-Based Regression](https://mlsanity.com/paper/2507.14997/) (2025)
- [No-Reference Image Contrast Assessment with Customized EfficientNet-B0](https://mlsanity.com/paper/2509.21967/) (2025)
- [DEAR: Dataset for Evaluating the Aesthetics of Rendering](https://mlsanity.com/paper/2512.05209/) (2025)
- [Image Quality Assessment: Exploring Quality Awareness via Memory-driven Distortion Patterns Matching](https://mlsanity.com/paper/2602.18000/) (2026)
- [Q-Tacit: Image Quality Assessment via Latent Visual Reasoning](https://mlsanity.com/paper/2603.22641/) (2026)
- [Spatially Localized Image Degradation Embeddings for Image Quality Assessment](https://mlsanity.com/paper/2606.29162/) (2026)
- [A Reference-Free Framework for Evaluating Single-Frame ISP Pipelines](https://mlsanity.com/paper/2607.23321/) (2026)

## Abstract (arXiv)

Multi-level deep-features have been driving state-of-the-art methods for aesthetics and image quality assessment (IQA). However, most IQA benchmarks are comprised of artificially distorted images, for which features derived from ImageNet under-perform. We propose a new IQA dataset and a weakly supervised feature learning approach to train features more suitable for IQA of artificially distorted images. The dataset, KADIS-700k, is far more extensive than similar works, consisting of 140,000 pristine images, 25 distortions types, totaling 700k distorted versions. Our weakly supervised feature learning is designed as a multi-task learning type training, using eleven existing full-reference IQA metrics as proxies for differential mean opinion scores. We also introduce a benchmark database, KADID-10k, of artificially degraded images, each subjectively annotated by 30 crowd workers. We make use of our derived image feature vectors for (no-reference) image quality assessment by training and testing a shallow regression network on this database and five other benchmark IQA databases. Our method, termed DeepFL-IQA, performs better than other feature-based no-reference IQA methods and also better than all tested full-reference IQA methods on KADID-10k. For the other five benchmark IQA databases, DeepFL-IQA matches the performance of the best existing end-to-end deep learning-based methods on average.