# Slimmable Compressive Autoencoders for Practical Neural Image Compression

arXiv: https://arxiv.org/abs/2103.15726 · HTML: https://mlsanity.com/paper/2103.15726/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 44 references that are in the map.
- First posted on arXiv 29 Mar 2021.

## Builds on (most cited first, 30 of 32)

- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [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)
- [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)
- [Slimmable Neural Networks](https://mlsanity.com/paper/1812.08928/) (2018)
- [Lossy Image Compression with Compressive Autoencoders](https://mlsanity.com/paper/1703.00395/) (2017)
- [Designing Neural Network Architectures using Reinforcement Learning](https://mlsanity.com/paper/1611.02167/) (2016)
- [Channel-wise Autoregressive Entropy Models for Learned Image Compression](https://mlsanity.com/paper/2007.08739/) (2020)
- [Universally Slimmable Networks and Improved Training Techniques](https://mlsanity.com/paper/1903.05134/) (2019)
- [Generative Adversarial Networks for Extreme Learned Image Compression](https://mlsanity.com/paper/1804.02958/) (2018)
- [Full Resolution Image Compression with Recurrent Neural Networks](https://mlsanity.com/paper/1608.05148/) (2016)
- [Variable Rate Image Compression with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06085/) (2015)
- [Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations](https://mlsanity.com/paper/1704.00648/) (2017)
- [Context-adaptive Entropy Model for End-to-end Optimized Image Compression](https://mlsanity.com/paper/1809.10452/) (2018)
- [Conditional Probability Models for Deep Image Compression](https://mlsanity.com/paper/1801.04260/) (2018)
- [Real-Time Adaptive Image Compression](https://mlsanity.com/paper/1705.05823/) (2017)
- [Density Modeling of Images using a Generalized Normalization Transformation](https://mlsanity.com/paper/1511.06281/) (2015)
- [Variable Rate Deep Image Compression With a Conditional Autoencoder](https://mlsanity.com/paper/1909.04802/) (2019)
- [Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks](https://mlsanity.com/paper/1703.10114/) (2017)
- [Learning Convolutional Networks for Content-weighted Image Compression](https://mlsanity.com/paper/1703.10553/) (2017)
- [Deep Generative Models for Distribution-Preserving Lossy Compression](https://mlsanity.com/paper/1805.11057/) (2018)
- [Variable Rate Deep Image Compression with Modulated Autoencoder](https://mlsanity.com/paper/1912.05526/) (2019)
- [Towards Conceptual Compression](https://mlsanity.com/paper/1604.08772/) (2016)
- [Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression](https://mlsanity.com/paper/1906.10057/) (2019)

## Built on by (most cited first, 30 of 39)

- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [EVC: Towards Real-Time Neural Image Compression with Mask Decay](https://mlsanity.com/paper/2302.05071/) (2023)
- [QARV: Quantization-Aware ResNet VAE for Lossy Image Compression](https://mlsanity.com/paper/2302.08899/) (2023)
- [DPICT: Deep Progressive Image Compression Using Trit-Planes](https://mlsanity.com/paper/2112.06334/) (2021)
- [3DAC: Learning Attribute Compression for Point Clouds](https://mlsanity.com/paper/2203.09931/) (2022)
- [Context-Based Trit-Plane Coding for Progressive Image Compression](https://mlsanity.com/paper/2303.05715/) (2023)
- [LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compression](https://mlsanity.com/paper/2304.12319/) (2023)
- [Causal Context Adjustment Loss for Learned Image Compression](https://mlsanity.com/paper/2410.04847/) (2024)
- [Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptation](https://mlsanity.com/paper/2406.00758/) (2024)
- [Content Adaptive Latents and Decoder for Neural Image Compression](https://mlsanity.com/paper/2212.10132/) (2022)
- [ProgDTD: Progressive Learned Image Compression with Double-Tail-Drop Training](https://mlsanity.com/paper/2305.02145/) (2023)
- [Generative Visual Compression: A Review](https://mlsanity.com/paper/2402.02140/) (2024)
- [LC-FDNet: Learned Lossless Image Compression with Frequency Decomposition Network](https://mlsanity.com/paper/2112.06417/) (2021)
- [Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Survey](https://mlsanity.com/paper/2405.01725/) (2024)
- [Efficient High-Resolution Deep Learning: A Survey](https://mlsanity.com/paper/2207.13050/) (2022)
- [Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression](https://mlsanity.com/paper/2411.16119/) (2024)
- [SlimFL: Federated Learning with Superposition Coding over Slimmable Neural Networks](https://mlsanity.com/paper/2203.14094/) (2022)
- [Exploring Resolution Fields for Scalable Image Compression with Uncertainty Guidance](https://mlsanity.com/paper/2306.08941/) (2023)
- [Generative Human Video Compression with Multi-granularity Temporal Trajectory Factorization](https://mlsanity.com/paper/2410.10171/) (2024)
- [Is JPEG AI going to change image forensics?](https://mlsanity.com/paper/2412.03261/) (2024)
- [An Efficient Adaptive Compression Method for Human Perception and Machine Vision Tasks](https://mlsanity.com/paper/2501.04329/) (2025)
- [Learning-Based Video Coding with Joint Deep Compression and Enhancement](https://mlsanity.com/paper/2111.14474/) (2021)
- [Exploring Structural Sparsity in Neural Image Compression](https://mlsanity.com/paper/2202.04595/) (2022)
- [SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision](https://mlsanity.com/paper/2207.06242/) (2022)
- [Neural Image Compression: Generalization, Robustness, and Spectral Biases](https://mlsanity.com/paper/2307.08657/) (2023)
- [ScrollNet: Dynamic Weight Importance for Continual Learning](https://mlsanity.com/paper/2308.16567/) (2023)
- [Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods](https://mlsanity.com/paper/2411.11795/) (2024)
- [Remote Inference over Dynamic Links via Adaptive Rate Deep Task-Oriented Vector Quantization](https://mlsanity.com/paper/2501.02521/) (2025)
- [DANICE: Domain adaptation without forgetting in neural image compression](https://mlsanity.com/paper/2104.09370/) (2021)
- [Slimmable Video Codec](https://mlsanity.com/paper/2205.06754/) (2022)

## Abstract (arXiv)

Neural image compression leverages deep neural networks to outperform traditional image codecs in rate-distortion performance. However, the resulting models are also heavy, computationally demanding and generally optimized for a single rate, limiting their practical use. Focusing on practical image compression, we propose slimmable compressive autoencoders (SlimCAEs), where rate (R) and distortion (D) are jointly optimized for different capacities. Once trained, encoders and decoders can be executed at different capacities, leading to different rates and complexities. We show that a successful implementation of SlimCAEs requires suitable capacity-specific RD tradeoffs. Our experiments show that SlimCAEs are highly flexible models that provide excellent rate-distortion performance, variable rate, and dynamic adjustment of memory, computational cost and latency, thus addressing the main requirements of practical image compression.