mlsanityData to 7 Oct 2026

Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations

arXiv 1704.00648 ↗First posted 3 Apr 2017cs.LG cs.CVcited by 149

Not on the map. Why?

Abstract (arXiv)

We present a new approach to learn compressible representations in deep architectures with an end-to-end training strategy. Our method is based on a soft (continuous) relaxation of quantization and entropy, which we anneal to their discrete counterparts throughout training. We showcase this method for two challenging applications: Image compression and neural network compression. While these tasks have typically been approached with different methods, our soft-to-hard quantization approach gives results competitive with the state-of-the-art for both.

Key facts. Cited by 149 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 31; 2022: 29; 2023: 27; 2024: 28; 2025: 21; 2026: 13.

149 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  3. 2021Implicit Neural Representations for Image Compressioncited by 161
  4. 2024Image and Video Tokenization with Binary Spherical Quantizationcited by 110
  5. 2021Enhanced Invertible Encoding for Learned Image Compressioncited by 102
  6. 2021SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Eventscited by 84
  7. 2022Memory Replay with Data Compression for Continual Learningcited by 80
  8. 2022An Introduction to Neural Data Compressioncited by 78
  9. 2022SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantizationcited by 68
  10. 2023Text + Sketch: Image Compression at Ultra Low Ratescited by 63
  11. 2021Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transformcited by 56
  12. 2021AdvDrop: Adversarial Attack to DNNs by Dropping Informationcited by 55
38 more
  1. 2023Online Clustered Codebookcited by 55
  2. 2022Unified Multivariate Gaussian Mixture for Efficient Neural Image Compressioncited by 43
  3. 2021Slimmable Compressive Autoencoders for Practical Neural Image Compressioncited by 38
  4. 2022DeepJSCC-Q: Constellation Constrained Deep Joint Source-Channel Codingcited by 36
  5. 2021Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modulescited by 33
  6. 2022Image Compression with Product Quantized Masked Image Modelingcited by 32
  7. 2021Extending Neural P-frame Codecs for B-frame Codingcited by 30
  8. 2023QuantEase: Optimization-based Quantization for Language Modelscited by 28
  9. 2021On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Frameworkcited by 27
  10. 2023HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayescited by 27
  11. 2023Zero-shot Generation of Coherent Storybook from Plain Text Story using Diffusion Modelscited by 26
  12. 20254DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Videocited by 26
  13. 2021DPICT: Deep Progressive Image Compression Using Trit-Planescited by 25
  14. 2024Residual Quantization with Implicit Neural Codebookscited by 24
  15. 2022Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compressioncited by 21
  16. 2023Context-Based Trit-Plane Coding for Progressive Image Compressioncited by 21
  17. 2024Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compressioncited by 21
  18. 2021Distance-aware Quantizationcited by 19
  19. 2023LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compressioncited by 19
  20. 2023Raw Image Reconstruction with Learned Compact Metadatacited by 18
  21. 2023Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AIcited by 17
  22. 2024A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generationcited by 17
  23. 2021Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeletoncited by 16
  24. 2023Neural Vector Fields: Implicit Representation by Explicit Learningcited by 16
  25. 2023EdVAE: Mitigating Codebook Collapse with Evidential Discrete Variational Autoencoderscited by 16
  26. 2022Advancing Learned Video Compression with In-loop Frame Predictioncited by 14
  27. 2023Multi-Modality Deep Network for Extreme Learned Image Compressioncited by 14
  28. 2023NVTC: Nonlinear Vector Transform Codingcited by 14
  29. 2024Prompt Sliders for Fine-Grained Control, Editing and Erasing of Concepts in Diffusion Modelscited by 14
  30. 2022Learning-Driven Lossy Image Compression; A Comprehensive Surveycited by 13
  31. 2022Optimally Controllable Perceptual Lossy Compressioncited by 13
  32. 2024HPC: Hierarchical Progressive Coding Framework for Volumetric Videocited by 13
  33. 2021Learning Cross-Scale Weighted Prediction for Efficient Neural Video Compressioncited by 12
  34. 2022Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utilitycited by 12
  35. 2023Semantically Structured Image Compression via Irregular Group-Based Decouplingcited by 12
  36. 2021A Cross Channel Context Model for Latents in Deep Image Compressioncited by 10
  37. 2025Lossy Neural Compression for Geospatial Analytics: A Reviewcited by 10
  38. 2021DeepJSCC-Q: Channel Input Constrained Deep Joint Source-Channel Codingcited by 9

50 most cited of 149 All 149 (JSON)