mlsanityData to 7 Oct 2026

Modality-Agnostic Variational Compression of Implicit Neural Representations

arXiv 2301.09479 ↗First posted 23 Jan 2023stat.ML cs.AI cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

We introduce a modality-agnostic neural compression algorithm based on a functional view of data and parameterised as an Implicit Neural Representation (INR). Bridging the gap between latent coding and sparsity, we obtain compact latent representations non-linearly mapped to a soft gating mechanism. This allows the specialisation of a shared INR network to each data item through subnetwork selection. After obtaining a dataset of such latent representations, we directly optimise the rate/distortion trade-off in a modality-agnostic space using neural compression. Variational Compression of Implicit Neural Representations (VC-INR) shows improved performance given the same representational capacity pre quantisation while also outperforming previous quantisation schemes used for other INR techniques. Our experiments demonstrate strong results over a large set of diverse modalities using the same algorithm without any modality-specific inductive biases. We show results on images, climate data, 3D shapes and scenes as well as audio and video, introducing VC-INR as the first INR-based method to outperform codecs as well-known and diverse as JPEG 2000, MP3 and AVC/HEVC on their respective modalities.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 47 of its 71 references that are in the map. First posted on arXiv 23 Jan 2023.

Builds on

47 of 71 references.

References · 47

  1. 2016Layer Normalizationcited by 5,579
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  6. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  7. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  8. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  9. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  10. 2018Variational image compression with a scale hyperpriorcited by 910
  11. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  12. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
35 more
  1. 2016End-to-end Optimized Image Compressioncited by 673
  2. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  3. 2017Self-Normalizing Neural Networkscited by 591
  4. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  5. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 550
  6. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 515
  7. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 377
  8. 2018How Does Batch Normalization Help Optimization?cited by 355
  9. 2018DVC: An End-to-end Deep Video Compression Frameworkcited by 324
  10. 2017Lossy Image Compression with Compressive Autoencoderscited by 289
  11. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 240
  12. 2021COIN: COmpression with Implicit Neural representationscited by 232
  13. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
  14. 2019Understanding and Improving Layer Normalizationcited by 213
  15. 2022Generating Videos with Dynamics-aware Implicit Generative Adversarial Networkscited by 186
  16. 2021Implicit Neural Representations for Image Compressioncited by 161
  17. 2021Modulated Periodic Activations for Generalizable Local Functional Representationscited by 140
  18. 2018Context-adaptive Entropy Model for End-to-end Optimized Image Compressioncited by 138
  19. 2020Adversarial Generation of Continuous Imagescited by 135
  20. 2015Density Modeling of Images using a Generalized Normalization Transformationcited by 123
  21. 2019Video Compression With Rate-Distortion Autoencoderscited by 97
  22. 2022Lossy Compression with Gaussian Diffusioncited by 87
  23. 2022An Introduction to Neural Data Compressioncited by 78
  24. 2020Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Networkcited by 74
  25. 2019Task Agnostic Continual Learning via Meta Learningcited by 53
  26. 2022COOL-CHIC: Coordinate-based Low Complexity Hierarchical Image Codeccited by 50
  27. 2021Powerpropagation: A sparsity inducing weight reparameterisationcited by 49
  28. 2021Meta-Learning Sparse Implicit Neural Representationscited by 48
  29. 2022Generalised Implicit Neural Representationscited by 31
  30. 2022Compressing multidimensional weather and climate data into neural networkscited by 31
  31. 2022Scalable Neural Video Representations with Learnable Positional Featurescited by 29
  32. 2022HyperTime: Implicit Neural Representation for Time Seriescited by 24
  33. 2022Meta-Learning Sparse Compression Networkscited by 22
  34. 2022On Quantizing Implicit Neural Representationscited by 20
  35. 2022Survey of Big Data sizes in 2021cited by 4

Built on by

Cited by year

Citing papers per year: 2023: 6; 2024: 13; 2025: 3.

22 papers.

Sort:

  1. 2023C3: High-performance and low-complexity neural compression from a single image or videocited by 54
  2. 2024Online Adaptation of Language Models with a Memory of Amortized Contextscited by 35
  3. 2023Compression with Bayesian Implicit Neural Representationscited by 25
  4. 2024Efficient Learning With Sine-Activated Low-rank Matricescited by 22
  5. 2024LEIA: Latent View-invariant Embeddings for Implicit 3D Articulationcited by 16
  6. 2024Nonparametric Teaching of Implicit Neural Representationscited by 13
  7. 2024Good, Cheap, and Fast: Overfitted Image Compression with Wasserstein Distortioncited by 13
  8. 2023Learning Large-scale Neural Fields via Context Pruned Meta-Learningcited by 12
  9. 2024Fast Training of Sinusoidal Neural Fields via Scaling Initializationcited by 11
  10. 2023RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representationscited by 9
  11. 2024Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semanticscited by 9
  12. 2023In Search of a Data Transformation That Accelerates Neural Field Trainingcited by 7
10 more
  1. 2023Improved Positional Encoding for Implicit Neural Representation based Compact Data Representationcited by 4
  2. 2024Accelerating Relative Entropy Coding with Space Partitioningcited by 4
  3. 2024Hybrid Neural Representations for Spherical Datacited by 3
  4. 2024Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Expertscited by 3
  5. 2025UAR-NVC: A Unified AutoRegressive Framework for Memory-Efficient Neural Video Compressioncited by 3
  6. 2025ARC: Anchored Representation Clouds for High-Resolution INR Classificationcited by 3
  7. 2025NTK-Guided Implicit Neural Teachingcited by 2
  8. 2024Implicit Neural Representations for Simultaneous Reduction and Continuous Reconstruction of Multi-Altitude Climate Datacited by 1
  9. 2024D'OH: Decoder-Only Random Hypernetworks for Implicit Neural Representationscited by 0
  10. 2024Efficient Compression of Sparse Accelerator Data Using Implicit Neural Representations and Importance Samplingcited by 0