# AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution

arXiv: https://arxiv.org/abs/2404.03296 · HTML: https://mlsanity.com/paper/2404.03296/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 52 references that are in the map.
- First posted on arXiv 4 Apr 2024.

## Builds on (most cited first, 30 of 34)

- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [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)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision](https://mlsanity.com/paper/1905.03696/) (2019)
- [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018)
- [Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks](https://mlsanity.com/paper/1908.05033/) (2019)
- [Lightweight Image Super-Resolution with Information Multi-distillation Network](https://mlsanity.com/paper/1909.11856/) (2019)
- [Low-bit Quantization of Neural Networks for Efficient Inference](https://mlsanity.com/paper/1902.06822/) (2019)
- [Fast and Accurate Single Image Super-Resolution via Information Distillation Network](https://mlsanity.com/paper/1803.09454/) (2018)
- [ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic](https://mlsanity.com/paper/2103.04039/) (2021)
- [Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search](https://mlsanity.com/paper/1901.07261/) (2019)
- [Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization](https://mlsanity.com/paper/2110.06554/) (2021)
- [DHP: Differentiable Meta Pruning via HyperNetworks](https://mlsanity.com/paper/2003.13683/) (2020)
- [Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance](https://mlsanity.com/paper/2203.08368/) (2022)
- [PAMS: Quantized Super-Resolution via Parameterized Max Scale](https://mlsanity.com/paper/2011.04212/) (2020)
- [Path-Restore: Learning Network Path Selection for Image Restoration](https://mlsanity.com/paper/1904.10343/) (2019)
- [Learning Frequency-aware Dynamic Network for Efficient Super-Resolution](https://mlsanity.com/paper/2103.08357/) (2021)
- [Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search](https://mlsanity.com/paper/2108.08910/) (2021)
- [AdderSR: Towards Energy Efficient Image Super-Resolution](https://mlsanity.com/paper/2009.08891/) (2020)
- [DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks](https://mlsanity.com/paper/2012.11230/) (2020)
- [Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices](https://mlsanity.com/paper/2105.10288/) (2021)
- [Efficient Super Resolution Using Binarized Neural Network](https://mlsanity.com/paper/1812.06378/) (2018)
- [CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution](https://mlsanity.com/paper/2207.10345/) (2022)
- [Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks](https://mlsanity.com/paper/2203.03844/) (2022)
- [Fully Quantized Image Super-Resolution Networks](https://mlsanity.com/paper/2011.14265/) (2020)
- [Adaptive Patch Exiting for Scalable Single Image Super-Resolution](https://mlsanity.com/paper/2203.11589/) (2022)
- [CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network with Large Input](https://mlsanity.com/paper/2304.06454/) (2023)

## Built on by (most cited first, 9 of 9)

- [Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications](https://mlsanity.com/paper/2508.15008/) (2025)
- [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)
- [Text Embedding Knows How to Quantize Text-Guided Diffusion Models](https://mlsanity.com/paper/2507.10340/) (2025)
- [LogicIR: Logic Gate Networks for Image Restoration](https://mlsanity.com/paper/2606.26609/) (2026)
- [Any Orthogonal Transform Will Do: Range Reduction Explains Rotation-Based Quantization for Super-Resolution](https://mlsanity.com/paper/2601.21069/) (2026)
- [Physically-Guided Optical Inversion Enable Non-Contact Side-Channel Attack on Isolated Screens](https://mlsanity.com/paper/2604.13419/) (2026)
- [QuantSR+: Pushing the Limit of Quantized Image Super-Resolution Networks](https://mlsanity.com/paper/2605.22351/) (2026)
- [Binarized High-Efficiency RAW Video Restoration and Beyond](https://mlsanity.com/paper/2608.16756/) (2026)

## Abstract (arXiv)

Although image super-resolution (SR) problem has experienced unprecedented restoration accuracy with deep neural networks, it has yet limited versatile applications due to the substantial computational costs. Since different input images for SR face different restoration difficulties, adapting computational costs based on the input image, referred to as adaptive inference, has emerged as a promising solution to compress SR networks. Specifically, adapting the quantization bit-widths has successfully reduced the inference and memory cost without sacrificing the accuracy. However, despite the benefits of the resultant adaptive network, existing works rely on time-intensive quantization-aware training with full access to the original training pairs to learn the appropriate bit allocation policies, which limits its ubiquitous usage. To this end, we introduce the first on-the-fly adaptive quantization framework that accelerates the processing time from hours to seconds. We formulate the bit allocation problem with only two bit mapping modules: one to map the input image to the image-wise bit adaptation factor and one to obtain the layer-wise adaptation factors. These bit mappings are calibrated and fine-tuned using only a small number of calibration images. We achieve competitive performance with the previous adaptive quantization methods, while the processing time is accelerated by x2000. Codes are available at https://github.com/Cheeun/AdaBM.