# On Efficient Transformer-Based Image Pre-training for Low-Level Vision

arXiv: https://arxiv.org/abs/2112.10175 · HTML: https://mlsanity.com/paper/2112.10175/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 88 references that are in the map.
- First posted on arXiv 19 Dec 2021.

## Builds on (most cited first, 30 of 48)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows](https://mlsanity.com/paper/2107.00652/) (2021)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)

## Built on by (most cited first, 30 of 64)

- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024)
- [Efficient and Explicit Modelling of Image Hierarchies for Image Restoration](https://mlsanity.com/paper/2303.00748/) (2023)
- [MambaIRv2: Attentive State Space Restoration](https://mlsanity.com/paper/2411.15269/) (2024)
- [SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution](https://mlsanity.com/paper/2208.11247/) (2022)
- [SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting](https://mlsanity.com/paper/2402.18848/) (2024)
- [HAT: Hybrid Attention Transformer for Image Restoration](https://mlsanity.com/paper/2309.05239/) (2023)
- [A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends](https://mlsanity.com/paper/2410.15067/) (2024)
- [A Comparative Study of Image Restoration Networks for General Backbone Network Design](https://mlsanity.com/paper/2310.11881/) (2023)
- [Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategy](https://mlsanity.com/paper/2401.03379/) (2024)
- [Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning](https://mlsanity.com/paper/2403.02601/) (2024)
- [MFDNet: Multi-Frequency Deflare Network for Efficient Nighttime Flare Removal](https://mlsanity.com/paper/2406.18079/) (2024)
- [Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution](https://mlsanity.com/paper/2410.10140/) (2024)
- [ReFIR: Grounding Large Restoration Models with Retrieval Augmentation](https://mlsanity.com/paper/2410.05601/) (2024)
- [Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformers](https://mlsanity.com/paper/2306.12992/) (2023)
- [Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach](https://mlsanity.com/paper/2401.05633/) (2024)
- [CausalSR: Structural Causal Model-Driven Super-Resolution with Counterfactual Inference](https://mlsanity.com/paper/2501.15852/) (2025)
- [WaveMixSR: A Resource-efficient Neural Network for Image Super-resolution](https://mlsanity.com/paper/2307.00430/) (2023)
- [Activating Wider Areas in Image Super-Resolution](https://mlsanity.com/paper/2403.08330/) (2024)
- [What Makes for Good Tokenizers in Vision Transformer?](https://mlsanity.com/paper/2212.11115/) (2022)
- [CDFormer:When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolution](https://mlsanity.com/paper/2405.07648/) (2024)
- [Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts](https://mlsanity.com/paper/2312.08881/) (2023)
- [A Survey on Future Frame Synthesis: Bridging Deterministic and Generative Approaches](https://mlsanity.com/paper/2401.14718/) (2024)
- [IPT-V2: Efficient Image Processing Transformer using Hierarchical Attentions](https://mlsanity.com/paper/2404.00633/) (2024)
- [Rethinking Image Super-Resolution from Training Data Perspectives](https://mlsanity.com/paper/2409.00768/) (2024)
- [Contourlet Refinement Gate Framework for Thermal Spectrum Distribution Regularized Infrared Image Super-Resolution](https://mlsanity.com/paper/2411.12530/) (2024)
- [Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution](https://mlsanity.com/paper/2407.16232/) (2024)
- [Emulating Self-attention with Convolution for Efficient Image Super-Resolution](https://mlsanity.com/paper/2503.06671/) (2025)
- [Enhancing Image Restoration Transformer via Adaptive Translation Equivariance](https://mlsanity.com/paper/2506.18520/) (2025)
- [Auto-Encoded Supervision for Perceptual Image Super-Resolution](https://mlsanity.com/paper/2412.00124/) (2024)

## Abstract (arXiv)

Pre-training has marked numerous state of the arts in high-level computer vision, while few attempts have ever been made to investigate how pre-training acts in image processing systems. In this paper, we tailor transformer-based pre-training regimes that boost various low-level tasks. To comprehensively diagnose the influence of pre-training, we design a whole set of principled evaluation tools that uncover its effects on internal representations. The observations demonstrate that pre-training plays strikingly different roles in low-level tasks. For example, pre-training introduces more local information to higher layers in super-resolution (SR), yielding significant performance gains, while pre-training hardly affects internal feature representations in denoising, resulting in limited gains. Further, we explore different methods of pre-training, revealing that multi-related-task pre-training is more effective and data-efficient than other alternatives. Finally, we extend our study to varying data scales and model sizes, as well as comparisons between transformers and CNNs-based architectures. Based on the study, we successfully develop state-of-the-art models for multiple low-level tasks. Code is released at https://github.com/fenglinglwb/EDT.