# Exploring Structural Sparsity in Neural Image Compression

arXiv: https://arxiv.org/abs/2202.04595 · HTML: https://mlsanity.com/paper/2202.04595/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 21 references that are in the map.
- First posted on arXiv 9 Feb 2022.

## Builds on (most cited first, 19 of 19)

- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [Slimmable Neural Networks](https://mlsanity.com/paper/1812.08928/) (2018)
- [CompressAI: a PyTorch library and evaluation platform for end-to-end compression research](https://mlsanity.com/paper/2011.03029/) (2020)
- [Density Modeling of Images using a Generalized Normalization Transformation](https://mlsanity.com/paper/1511.06281/) (2015)
- [Non-local Attention Optimized Deep Image Compression](https://mlsanity.com/paper/1904.09757/) (2019)
- [Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation](https://mlsanity.com/paper/2003.02012/) (2020)
- [Dynamic Slimmable Network](https://mlsanity.com/paper/2103.13258/) (2021)
- [Channel Gating Neural Networks](https://mlsanity.com/paper/1805.12549/) (2018)
- [Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation](https://mlsanity.com/paper/2003.08866/) (2020)
- [Effective Sparsification of Neural Networks with Global Sparsity Constraint](https://mlsanity.com/paper/2105.01571/) (2021)
- [Slimmable Compressive Autoencoders for Practical Neural Image Compression](https://mlsanity.com/paper/2103.15726/) (2021)
- [Computationally Efficient Neural Image Compression](https://mlsanity.com/paper/1912.08771/) (2019)
- [Deep Residual Learning for Image Compression](https://mlsanity.com/paper/1906.09731/) (2019)
- [Channel-Level Variable Quantization Network for Deep Image Compression](https://mlsanity.com/paper/2007.12619/) (2020)
- [Universal Efficient Variable-rate Neural Image Compression](https://mlsanity.com/paper/2111.11305/) (2021)

## Built on by (most cited first, 4 of 4)

- [Forget the Data and Fine-Tuning! Just Fold the Network to Compress](https://mlsanity.com/paper/2502.10216/) (2025)
- [Generative Human Video Compression with Multi-granularity Temporal Trajectory Factorization](https://mlsanity.com/paper/2410.10171/) (2024)
- [Neural Image Compression: Generalization, Robustness, and Spectral Biases](https://mlsanity.com/paper/2307.08657/) (2023)
- [Accelerating Learnt Video Codecs with Gradient Decay and Layer-wise Distillation](https://mlsanity.com/paper/2312.02605/) (2023)

## Abstract (arXiv)

Neural image compression have reached or out-performed traditional methods (such as JPEG, BPG, WebP). However,their sophisticated network structures with cascaded convolution layers bring heavy computational burden for practical deployment. In this paper, we explore the structural sparsity in neural image compression network to obtain real-time acceleration without any specialized hardware design or algorithm. We propose a simple plug-in adaptive binary channel masking(ABCM) to judge the importance of each convolution channel and introduce sparsity during training. During inference, the unimportant channels are pruned to obtain slimmer network and less computation. We implement our method into three neural image compression networks with different entropy models to verify its effectiveness and generalization, the experiment results show that up to 7x computation reduction and 3x acceleration can be achieved with negligible performance drop.