# Q-LIC: Quantizing Learned Image Compression with Channel Splitting

arXiv: https://arxiv.org/abs/2205.14510 · HTML: https://mlsanity.com/paper/2205.14510/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 66 references that are in the map.
- First posted on arXiv 28 May 2022.

## Builds on (most cited first, 30 of 38)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [Channel-wise Autoregressive Entropy Models for Learned Image Compression](https://mlsanity.com/paper/2007.08739/) (2020)
- [Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights](https://mlsanity.com/paper/1702.03044/) (2017)
- [Trained Ternary Quantization](https://mlsanity.com/paper/1612.01064/) (2016)
- [Compressing Deep Convolutional Networks using Vector Quantization](https://mlsanity.com/paper/1412.6115/) (2014)
- [Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Loss](https://mlsanity.com/paper/1808.05779/) (2018)
- [Context-adaptive Entropy Model for End-to-end Optimized Image Compression](https://mlsanity.com/paper/1809.10452/) (2018)
- [Deep Learning with Low Precision by Half-wave Gaussian Quantization](https://mlsanity.com/paper/1702.00953/) (2017)
- [Non-local Attention Optimized Deep Image Compression](https://mlsanity.com/paper/1904.09757/) (2019)
- [Network Quantization with Element-wise Gradient Scaling](https://mlsanity.com/paper/2104.00903/) (2021)
- [Image and Video Compression with Neural Networks: A Review](https://mlsanity.com/paper/1904.03567/) (2019)
- [Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation](https://mlsanity.com/paper/2111.14826/) (2021)
- [Causal Contextual Prediction for Learned Image Compression](https://mlsanity.com/paper/2011.09704/) (2020)
- [Learning End-to-End Lossy Image Compression: A Benchmark](https://mlsanity.com/paper/2002.03711/) (2020)
- [Value-aware Quantization for Training and Inference of Neural Networks](https://mlsanity.com/paper/1804.07802/) (2018)
- [WRPN: Wide Reduced-Precision Networks](https://mlsanity.com/paper/1709.01134/) (2017)
- [Learnable Companding Quantization for Accurate Low-bit Neural Networks](https://mlsanity.com/paper/2103.07156/) (2021)
- [BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization](https://mlsanity.com/paper/2102.10462/) (2021)

## Built on by (most cited first, 10 of 10)

- [MobileNVC: Real-time 1080p Neural Video Compression on a Mobile Device](https://mlsanity.com/paper/2310.01258/) (2023)
- [Rate-Distortion Optimized Post-Training Quantization for Learned Image Compression](https://mlsanity.com/paper/2211.02854/) (2022)
- [Accelerating Learnt Video Codecs with Gradient Decay and Layer-wise Distillation](https://mlsanity.com/paper/2312.02605/) (2023)
- [Flexible Mixed Precision Quantization for Learned Image Compression](https://mlsanity.com/paper/2506.01221/) (2025)
- [Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimization](https://mlsanity.com/paper/2405.14221/) (2024)
- [Rethinking Learned Image Compression: Context is All You Need](https://mlsanity.com/paper/2407.11590/) (2024)
- [JOMP: Jointly-Optimized Mixed-Precision Quantization Across Neural Video Coding Frameworks and Buffering Strategies](https://mlsanity.com/paper/2606.13110/) (2026)
- [Dual-Constrained Diffusion Image Compression for Operational Rate-Distortion-Perception Optimization](https://mlsanity.com/paper/2606.13366/) (2026)
- [Hadamard-Domain Model Quantization for Learned Image Coding](https://mlsanity.com/paper/2608.01653/) (2026)
- [HAMP-LIC: Hessian-Aware Mixed-Precision Post-Training Quantization for Learned Image Compression](https://mlsanity.com/paper/2608.12239/) (2026)

## Abstract (arXiv)

Learned image compression (LIC) has reached a comparable coding gain with traditional hand-crafted methods such as VVC intra. However, the large network complexity prohibits the usage of LIC on resource-limited embedded systems. Network quantization is an efficient way to reduce the network burden. This paper presents a quantized LIC (QLIC) by channel splitting. First, we explore that the influence of quantization error to the reconstruction error is different for various channels. Second, we split the channels whose quantization has larger influence to the reconstruction error. After the splitting, the dynamic range of channels is reduced so that the quantization error can be reduced. Finally, we prune several channels to keep the number of overall channels as origin. By using the proposal, in the case of 8-bit quantization for weight and activation of both main and hyper path, we can reduce the BD-rate by 0.61%-4.74% compared with the previous QLIC. Besides, we can reach better coding gain compared with the state-of-the-art network quantization method when quantizing MS-SSIM models. Moreover, our proposal can be combined with other network quantization methods to further improve the coding gain. The moderate coding loss caused by the quantization validates the feasibility of the hardware implementation for QLIC in the future.