mlsanityData to 7 Oct 2026

Slimmable Compressive Autoencoders for Practical Neural Image Compression

arXiv 2103.15726 ↗First posted 29 Mar 2021eess.IV cs.CVcited by 38

Not on the map. Why?

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.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 32 of its 44 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

32 of 44 references.

References · 32

  1. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  2. 2014Going Deeper with Convolutionscited by 4,231
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  4. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  5. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  6. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  7. 2018Variational image compression with a scale hyperpriorcited by 910
  8. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  9. 2016End-to-end Optimized Image Compressioncited by 673
  10. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  11. 2018Slimmable Neural Networkscited by 301
  12. 2017Lossy Image Compression with Compressive Autoencoderscited by 289
20 more
  1. 2016Designing Neural Network Architectures using Reinforcement Learningcited by 277
  2. 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 255
  3. 2019Universally Slimmable Networks and Improved Training Techniquescited by 219
  4. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
  5. 2016Full Resolution Image Compression with Recurrent Neural Networkscited by 170
  6. 2015Variable Rate Image Compression with Recurrent Neural Networkscited by 168
  7. 2017Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representationscited by 149
  8. 2018Context-adaptive Entropy Model for End-to-end Optimized Image Compressioncited by 138
  9. 2018Conditional Probability Models for Deep Image Compressioncited by 128
  10. 2017Real-Time Adaptive Image Compressioncited by 127
  11. 2015Density Modeling of Images using a Generalized Normalization Transformationcited by 123
  12. 2019Variable Rate Deep Image Compression With a Conditional Autoencodercited by 109
  13. 2017Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networkscited by 91
  14. 2017Learning Convolutional Networks for Content-weighted Image Compressioncited by 73
  15. 2018Deep Generative Models for Distribution-Preserving Lossy Compressioncited by 59
  16. 2019Variable Rate Deep Image Compression with Modulated Autoencodercited by 39
  17. 2016Towards Conceptual Compressioncited by 36
  18. 2019Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compressioncited by 33
  19. 2019Computationally Efficient Neural Image Compressioncited by 31
  20. 2018Neural Multi-scale Image Compressioncited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 8; 2023: 7; 2024: 10; 2025: 7; 2026: 2.

38 papers.

Sort:

By area:

  1. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 296
  2. 2023EVC: Towards Real-Time Neural Image Compression with Mask Decaycited by 46
  3. 2021DPICT: Deep Progressive Image Compression Using Trit-Planescited by 25
  4. 20223DAC: Learning Attribute Compression for Point Cloudscited by 22
  5. 2023Context-Based Trit-Plane Coding for Progressive Image Compressioncited by 21
  6. 2023LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compressioncited by 19
  7. 2024Causal Context Adjustment Loss for Learned Image Compressioncited by 19
  8. 2024Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptationcited by 15
  9. 2022Content Adaptive Latents and Decoder for Neural Image Compressioncited by 14
  10. 2023ProgDTD: Progressive Learned Image Compression with Double-Tail-Drop Trainingcited by 13
  11. 2024Generative Visual Compression: A Reviewcited by 13
  12. 2021LC-FDNet: Learned Lossless Image Compression with Frequency Decomposition Networkcited by 12
26 more
  1. 2024Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Surveycited by 10
  2. 2022Efficient High-Resolution Deep Learning: A Surveycited by 9
  3. 2024Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compressioncited by 8
  4. 2022SlimFL: Federated Learning with Superposition Coding over Slimmable Neural Networkscited by 6
  5. 2023Exploring Resolution Fields for Scalable Image Compression with Uncertainty Guidancecited by 6
  6. 2024Generative Human Video Compression with Multi-granularity Temporal Trajectory Factorizationcited by 5
  7. 2025An Efficient Adaptive Compression Method for Human Perception and Machine Vision Taskscited by 5
  8. 2021Learning-Based Video Coding with Joint Deep Compression and Enhancementcited by 4
  9. 2022Exploring Structural Sparsity in Neural Image Compressioncited by 4
  10. 2022SlimSeg: Slimmable Semantic Segmentation with Boundary Supervisioncited by 4
  11. 2023Neural Image Compression: Generalization, Robustness, and Spectral Biasescited by 4
  12. 2023ScrollNet: Dynamic Weight Importance for Continual Learningcited by 4
  13. 2024Is JPEG AI going to change image forensics?cited by 4
  14. 2024Exploring adversarial robustness of JPEG AI: methodology, comparison and new methodscited by 3
  15. 2025Remote Inference over Dynamic Links via Adaptive Rate Deep Task-Oriented Vector Quantizationcited by 3
  16. 2021DANICE: Domain adaptation without forgetting in neural image compressioncited by 2
  17. 2022Slimmable Video Codeccited by 2
  18. 2024Channel-Aware Throughput Maximization for Cooperative Data Fusion in CAVcited by 2
  19. 2025Learned Rate Control for Frame-Level Adaptive Neural Video Compression via Dynamic Neural Networkcited by 2
  20. 2025Bitstream Collisions in Neural Image Compression via Adversarial Perturbationscited by 1
  21. 2025All-in-One Transferring Image Compression from Human Perception to Multi-Machine Perceptioncited by 1
  22. 2025NIC-RobustBench: A Comprehensive Open-Source Toolkit for Neural Image Compression and Robustness Analysiscited by 1
  23. 2024FLLIC: Functionally Lossless Image Compressioncited by 0
  24. 2025HyperVQ: Enabling Hyperprior Entropy Modeling for VQ-Based Generative Image Compressioncited by 0
  25. 2026Joint Degradation-Aware Arbitrary-Scale Super-Resolution for Variable-Rate Extreme Image Compressioncited by 0
  26. 2026Scalable Neural Video Representation Compressioncited by 0