mlsanityData to 14 Oct 2026

Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction

arXiv 1611.09842 ↗First posted 29 Nov 2016cs.CVcited by 217

Not on the map. Why?

Abstract (arXiv)

We propose split-brain autoencoders, a straightforward modification of the traditional autoencoder architecture, for unsupervised representation learning. The method adds a split to the network, resulting in two disjoint sub-networks. Each sub-network is trained to perform a difficult task -- predicting one subset of the data channels from another. Together, the sub-networks extract features from the entire input signal. By forcing the network to solve cross-channel prediction tasks, we induce a representation within the network which transfers well to other, unseen tasks. This method achieves state-of-the-art performance on several large-scale transfer learning benchmarks.

Key facts. Cited by 217 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 87; 2022: 73; 2023: 35; 2024: 11; 2025: 6; 2026: 4.

217 papers.

Sort:

By area:

  1. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
  2. 2021VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Textcited by 429
  3. 2021Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learningcited by 372
  4. 2022Masked Siamese Networks for Label-Efficient Learningcited by 302
  5. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  6. 2023A Cookbook of Self-Supervised Learningcited by 250
  7. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  8. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 207
  9. 2021Reinforcement Learning with Prototypical Representationscited by 179
  10. 2021BEVT: BERT Pretraining of Video Transformerscited by 169
  11. 2021Efficient Visual Pretraining with Contrastive Detectioncited by 150
  12. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
38 more
  1. 2021Efficient Self-supervised Vision Transformers for Representation Learningcited by 149
  2. 2022Self-supervised Learning in Remote Sensing: A Reviewcited by 137
  3. 2021SAT: 2D Semantics Assisted Training for 3D Visual Groundingcited by 124
  4. 2021Mixed supervision for surface-defect detection: from weakly to fully supervised learningcited by 101
  5. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 99
  6. 2021SiT: Self-supervised vIsion Transformercited by 99
  7. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 99
  8. 2023Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modelingcited by 94
  9. 2022Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillationcited by 93
  10. 2021When Does Contrastive Visual Representation Learning Work?cited by 92
  11. 2021Learning to See by Looking at Noisecited by 92
  12. 2021Ensembling Off-the-shelf Models for GAN Trainingcited by 86
  13. 2021Divide and Contrast: Self-supervised Learning from Uncurated Datacited by 85
  14. 2021Robust Audio-Visual Instance Discriminationcited by 80
  15. 2022Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervisioncited by 80
  16. 2022Object discovery and representation networkscited by 80
  17. 2021Self-supervised learning methods and applications in medical imaging analysis: A surveycited by 77
  18. 2021Skeleton-Contrastive 3D Action Representation Learningcited by 76
  19. 2021Unsupervised Object-Level Representation Learning from Scene Imagescited by 72
  20. 2022Masked Frequency Modeling for Self-Supervised Visual Pre-Trainingcited by 71
  21. 2022Self-Supervised Visual Representation Learning with Semantic Groupingcited by 70
  22. 2021Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labelscited by 69
  23. 2021Mean Shift for Self-Supervised Learningcited by 65
  24. 2021Category Contrast for Unsupervised Domain Adaptation in Visual Taskscited by 65
  25. 2023Ti-MAE: Self-Supervised Masked Time Series Autoencoderscited by 63
  26. 2021Do Different Tracking Tasks Require Different Appearance Models?cited by 62
  27. 2021Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse Contextscited by 60
  28. 2022Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Frameworkcited by 59
  29. 2021Self-Supervised Learning of Remote Sensing Scene Representations Using Contrastive Multiview Codingcited by 58
  30. 2022A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyondcited by 58
  31. 2021Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Datacited by 55
  32. 2021UniMiSS: Universal Medical Self-Supervised Learning via Breaking Dimensionality Barriercited by 55
  33. 2022Robust Cross-Modal Representation Learning with Progressive Self-Distillationcited by 55
  34. 2022Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Seriescited by 54
  35. 2022UniCLIP: Unified Framework for Contrastive Language-Image Pre-trainingcited by 54
  36. 2021Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptionscited by 53
  37. 2021Human Hands as Probes for Interactive Object Understandingcited by 52
  38. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52

50 most cited of 217 All 217 (JSON)