mlsanityData to 14 Oct 2026

Invertible Residual Networks

arXiv 1811.00995 ↗First posted 2 Nov 2018cs.LG cs.AI cs.CVcited by 365

Not on the map. Why?

Abstract (arXiv)

We show that standard ResNet architectures can be made invertible, allowing the same model to be used for classification, density estimation, and generation. Typically, enforcing invertibility requires partitioning dimensions or restricting network architectures. In contrast, our approach only requires adding a simple normalization step during training, already available in standard frameworks. Invertible ResNets define a generative model which can be trained by maximum likelihood on unlabeled data. To compute likelihoods, we introduce a tractable approximation to the Jacobian log-determinant of a residual block. Our empirical evaluation shows that invertible ResNets perform competitively with both state-of-the-art image classifiers and flow-based generative models, something that has not been previously achieved with a single architecture.

Key facts. Cited by 365 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 90; 2022: 69; 2023: 65; 2024: 52; 2025: 42; 2026: 47.

365 papers.

Sort:

By area:

  1. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 312
  2. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 252
  3. 2022CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusioncited by 223
  4. 2021Sinkformers: Transformers with Doubly Stochastic Attentioncited by 138
  5. 2023Score-Based Diffusion Models as Principled Priors for Inverse Imagingcited by 127
  6. 2023End-to-End Diffusion Latent Optimization Improves Classifier Guidancecited by 108
  7. 2021Deep Generative Learning via Schr"odinger Bridgecited by 104
  8. 2021Neural Flows: Efficient Alternative to Neural ODEscited by 101
  9. 2021On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertaintycited by 87
  10. 2021On Training Implicit Modelscited by 75
  11. 2021Efficient and Accurate Gradients for Neural SDEscited by 71
  12. 2021Invertible Denoising Network: A Light Solution for Real Noise Removalcited by 68
38 more
  1. 2022Verifying the Union of Manifolds Hypothesis for Image Datacited by 64
  2. 2021Continual Learning via Local Module Compositioncited by 63
  3. 2021On the Practicality of Deterministic Epistemic Uncertaintycited by 62
  4. 2022Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanismscited by 61
  5. 2021A Dynamical System Perspective for Lipschitz Neural Networkscited by 60
  6. 2022Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attackscited by 60
  7. 2022CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphismcited by 57
  8. 2022Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Cameracited by 57
  9. 2021Rectangular Flows for Manifold Learningcited by 50
  10. 2022Score-based Generative Modeling Secretly Minimizes the Wasserstein Distancecited by 50
  11. 2021Densely connected normalizing flowscited by 49
  12. 2022A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awarenesscited by 49
  13. 2023How Smooth Is Attention?cited by 44
  14. 2021MALI: A memory efficient and reverse accurate integrator for Neural ODEscited by 42
  15. 2021Resampling Base Distributions of Normalizing Flowscited by 42
  16. 2021Reachability Analysis of Neural Feedback Loopscited by 41
  17. 2022Normalizing flow neural networks by JKO schemecited by 39
  18. 2021Momentum Residual Neural Networkscited by 37
  19. 2024Denoising: A Powerful Building-Block for Imaging, Inverse Problems, and Machine Learningcited by 35
  20. 2023Convergence of flow-based generative models via proximal gradient descent in Wasserstein spacecited by 34
  21. 2021Featurized Density Ratio Estimationcited by 33
  22. 2023Reversible Vision Transformerscited by 33
  23. 2023Autoregressive Conditional Neural Processescited by 33
  24. 2021Stochastic Normalizing Flows for Inverse Problems: a Markov Chains Viewpointcited by 32
  25. 2021Constructing Neural Network-Based Models for Simulating Dynamical Systemscited by 31
  26. 2023Universality and Limitations of Prompt Tuningcited by 30
  27. 2021Self-learning Machines based on Hamiltonian Echo Backpropagationcited by 28
  28. 2021Implicit Normalizing Flowscited by 28
  29. 2021JEM++: Improved Techniques for Training JEMcited by 28
  30. 2022Diagnosing and Fixing Manifold Overfitting in Deep Generative Modelscited by 28
  31. 2023A Unified Framework for U-Net Design and Analysiscited by 27
  32. 2023Fast Inference and Update of Probabilistic Density Estimation on Trajectory Predictioncited by 27
  33. 2021ECINN: Efficient Counterfactuals from Invertible Neural Networkscited by 26
  34. 2023Free-form Flows: Make Any Architecture a Normalizing Flowcited by 26
  35. 2021Benchmarking Invertible Architectures on Inverse Problemscited by 25
  36. 2022Deep Koopman Operator with Control for Nonlinear Systemscited by 25
  37. 2022Semi-supervised Invertible Neural Operators for Bayesian Inverse Problemscited by 25
  38. 2023CAP-VSTNet: Content Affinity Preserved Versatile Style Transfercited by 24

50 most cited of 365 All 365 (JSON)