mlsanityData to 14 Oct 2026

Autoencoding beyond pixels using a learned similarity metric

arXiv 1512.09300 ↗First posted 31 Dec 2015cs.LG cs.CV stat.MLcited by 407

Not on the map. Why?

Cited by 49 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the GAN discriminator as basis for the VAE reconstruction objective. Thereby, we replace element-wise errors with feature-wise errors to better capture the data distribution while offering invariance towards e.g. translation. We apply our method to images of faces and show that it outperforms VAEs with element-wise similarity measures in terms of visual fidelity. Moreover, we show that the method learns an embedding in which high-level abstract visual features (e.g. wearing glasses) can be modified using simple arithmetic.

Key facts. Cited by 407 papers in the map (data through 14 Oct 2026). First posted on arXiv 31 Dec 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 97; 2022: 91; 2023: 77; 2024: 53; 2025: 57; 2026: 31.

407 papers.

Sort:

By area:

  1. 2023Steering Language Models With Activation Engineeringcited by 922
  2. 2022Transformers are Sample-Efficient World Modelscited by 328
  3. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 321
  4. 2022Brain Imaging Generation with Latent Diffusion Modelscited by 268
  5. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 252
  6. 2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 251
  7. 2021Speech Resynthesis from Discrete Disentangled Self-Supervised Representationscited by 243
  8. 2025AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoderscited by 218
  9. 2021Neural Head Avatars from Monocular RGB Videoscited by 213
  10. 2021A Survey on Neural Speech Synthesiscited by 184
  11. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  12. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
38 more
  1. 2021DriveGAN: Towards a Controllable High-Quality Neural Simulationcited by 125
  2. 2021Image-to-Image Translation: Methods and Applicationscited by 116
  3. 2022Disentangled Representation Learningcited by 112
  4. 2021Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoderscited by 109
  5. 2018Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flowcited by 105
  6. 2021D2C: Diffusion-Denoising Models for Few-shot Conditional Generationcited by 96
  7. 2025Masked Autoencoders Are Effective Tokenizers for Diffusion Modelscited by 96
  8. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  9. 2021Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editingcited by 91
  10. 2022Fusing Global and Local Features for Generalized AI-Synthesized Image Detectioncited by 88
  11. 2022FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversioncited by 80
  12. 2025SAEs Are Good for Steering -- If You Select the Right Featurescited by 78
  13. 2022Synthesizing Informative Training Samples with GANcited by 77
  14. 2024Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categoriescited by 77
  15. 2021RAVE: A variational autoencoder for fast and high-quality neural audio synthesiscited by 73
  16. 2023To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Reviewcited by 72
  17. 2021Shelf-Supervised Mesh Prediction in the Wildcited by 65
  18. 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
  19. 2023LayoutDM: Transformer-based Diffusion Model for Layout Generationcited by 57
  20. 2024SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizercited by 56
  21. 2022Multiple Instance Learning for Digital Pathology: A Review on the State-of-the-Art, Limitations & Future Potentialcited by 54
  22. 2023Video Event Restoration Based on Keyframes for Video Anomaly Detectioncited by 54
  23. 2021Multimodal Image Synthesis and Editing: The Generative AI Eracited by 52
  24. 2021Stochastic Image-to-Video Synthesis using cINNscited by 49
  25. 2022HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancementcited by 49
  26. 2023Deep Learning Approaches for Data Augmentation in Medical Imaging: A Reviewcited by 48
  27. 2021HumanGAN: A Generative Model of Humans Imagescited by 47
  28. 2021Universal Rate-Distortion-Perception Representations for Lossy Compressioncited by 47
  29. 2022JPEG Artifact Correction using Denoising Diffusion Restoration Modelscited by 47
  30. 2022DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANscited by 43
  31. 2021DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfercited by 39
  32. 2022Spatially-Adaptive Multilayer Selection for GAN Inversion and Editingcited by 39
  33. 2022Quantized GAN for Complex Music Generation from Dance Videoscited by 37
  34. 20243D MedDiffusion: A 3D Medical Latent Diffusion Model for Controllable and High-quality Medical Image Generationcited by 37
  35. 2024A survey of synthetic data augmentation methods in computer visioncited by 34
  36. 2024Autoregressive Diffusion Transformer for Text-to-Speech Synthesiscited by 34
  37. 2022iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transformcited by 32
  38. 2023Generative Semantic Segmentationcited by 32

50 most cited of 407 All 407 (JSON)