# Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks

arXiv: https://arxiv.org/abs/2203.03844 · HTML: https://mlsanity.com/paper/2203.03844/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 49 references that are in the map.
- First posted on arXiv 8 Mar 2022.

## Builds on (most cited first, 30 of 33)

- [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)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [Deeply-Recursive Convolutional Network for Image Super-Resolution](https://mlsanity.com/paper/1511.04491/) (2015)
- [HRank: Filter Pruning using High-Rank Feature Map](https://mlsanity.com/paper/2002.10179/) (2020)
- [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018)
- [Lightweight Image Super-Resolution with Information Multi-distillation Network](https://mlsanity.com/paper/1909.11856/) (2019)
- [Deep Back-Projection Networks For Super-Resolution](https://mlsanity.com/paper/1803.02735/) (2018)
- [ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions](https://mlsanity.com/paper/2003.03488/) (2020)
- [Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Loss](https://mlsanity.com/paper/1808.05779/) (2018)
- [Bayesian Bits: Unifying Quantization and Pruning](https://mlsanity.com/paper/2005.07093/) (2020)
- [Rotated Binary Neural Network](https://mlsanity.com/paper/2009.13055/) (2020)
- [PAMS: Quantized Super-Resolution via Parameterized Max Scale](https://mlsanity.com/paper/2011.04212/) (2020)
- [IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization](https://mlsanity.com/paper/2111.09136/) (2021)
- [DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks](https://mlsanity.com/paper/2012.11230/) (2020)

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

- [Temporal Dynamic Quantization for Diffusion Models](https://mlsanity.com/paper/2306.02316/) (2023)
- [NIPQ: Noise proxy-based Integrated Pseudo-Quantization](https://mlsanity.com/paper/2206.00820/) (2022)
- [I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization](https://mlsanity.com/paper/2311.10126/) (2023)
- [DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers](https://mlsanity.com/paper/2408.03291/) (2024)
- [CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network with Large Input](https://mlsanity.com/paper/2304.06454/) (2023)
- [Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution](https://mlsanity.com/paper/2308.05022/) (2023)
- [AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution](https://mlsanity.com/paper/2404.03296/) (2024)
- [RefQSR: Reference-based Quantization for Image Super-Resolution Networks](https://mlsanity.com/paper/2404.01690/) (2024)
- [Overcoming Distribution Mismatch in Quantizing Image Super-Resolution Networks](https://mlsanity.com/paper/2307.13337/) (2023)
- [Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues](https://mlsanity.com/paper/2409.14330/) (2024)
- [Outlier-Aware Post-Training Quantization for Image Super-Resolution](https://mlsanity.com/paper/2511.00682/) (2025)
- [AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization](https://mlsanity.com/paper/2503.03088/) (2025)
- [ProfilingAgent: Profiling-Guided Agentic Reasoning for Adaptive Model Optimization](https://mlsanity.com/paper/2509.05584/) (2025)
- [E2FIF: Push the limit of Binarized Deep Imagery Super-resolution using End-to-end Full-precision Information Flow](https://mlsanity.com/paper/2207.06893/) (2022)
- [DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution](https://mlsanity.com/paper/2212.07613/) (2022)
- [Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution Networks](https://mlsanity.com/paper/2305.05888/) (2023)
- [Image super-resolution via dynamic network](https://mlsanity.com/paper/2310.10413/) (2023)
- [Decoder-Free Distillation for Quantized Image Restoration](https://mlsanity.com/paper/2603.09624/) (2026)
- [SINF: Semantic Neural Network Inference with Semantic Subgraphs](https://mlsanity.com/paper/2310.01259/) (2023)
- [SONIQ: System-Optimized Noise-Injected Ultra-Low-Precision Quantization with Full-Precision Parity](https://mlsanity.com/paper/2311.14114/) (2023)
- [Any Orthogonal Transform Will Do: Range Reduction Explains Rotation-Based Quantization for Super-Resolution](https://mlsanity.com/paper/2601.21069/) (2026)

## Abstract (arXiv)

Light-weight super-resolution (SR) models have received considerable attention for their serviceability in mobile devices. Many efforts employ network quantization to compress SR models. However, these methods suffer from severe performance degradation when quantizing the SR models to ultra-low precision (e.g., 2-bit and 3-bit) with the low-cost layer-wise quantizer. In this paper, we identify that the performance drop comes from the contradiction between the layer-wise symmetric quantizer and the highly asymmetric activation distribution in SR models. This discrepancy leads to either a waste on the quantization levels or detail loss in reconstructed images. Therefore, we propose a novel activation quantizer, referred to as Dynamic Dual Trainable Bounds (DDTB), to accommodate the asymmetry of the activations. Specifically, DDTB innovates in: 1) A layer-wise quantizer with trainable upper and lower bounds to tackle the highly asymmetric activations. 2) A dynamic gate controller to adaptively adjust the upper and lower bounds at runtime to overcome the drastically varying activation ranges over different samples.To reduce the extra overhead, the dynamic gate controller is quantized to 2-bit and applied to only part of the SR networks according to the introduced dynamic intensity. Extensive experiments demonstrate that our DDTB exhibits significant performance improvements in ultra-low precision. For example, our DDTB achieves a 0.70dB PSNR increase on Urban100 benchmark when quantizing EDSR to 2-bit and scaling up output images to x4. Code is at urlhttps://github.com/zysxmu/DDTB.