mlsanityData to 7 Oct 2026

Multiple Random Masking Autoencoder Ensembles for Robust Multimodal Semi-supervised Learning

arXiv 2402.08035 ↗First posted 12 Feb 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

There is an increasing number of real-world problems in computer vision and machine learning requiring to take into consideration multiple interpretation layers (modalities or views) of the world and learn how they relate to each other. For example, in the case of Earth Observations from satellite data, it is important to be able to predict one observation layer (e.g. vegetation index) from other layers (e.g. water vapor, snow cover, temperature etc), in order to best understand how the Earth System functions and also be able to reliably predict information for one layer when the data is missing (e.g. due to measurement failure or error).

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 41 references that are in the map. First posted on arXiv 12 Feb 2024.

Builds on

23 of 41 references.

References · 23

  1. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  2. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  3. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
  4. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 376
  5. 2022MultiMAE: Multi-modal Multi-task Masked Autoencoderscited by 287
  6. 2018The Sound of Pixelscited by 258
  7. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  8. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  9. 2021Efficiently Identifying Task Groupings for Multi-Task Learningcited by 218
  10. 2016Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Predictioncited by 217
  11. 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 208
  12. 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
11 more
  1. 2020Semantically-Guided Representation Learning for Self-Supervised Monocular Depthcited by 134
  2. 2019Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Cameracited by 130
  3. 20234M: Massively Multimodal Masked Modelingcited by 118
  4. 2020Robust Learning Through Cross-Task Consistencycited by 105
  5. 2018Deflecting Adversarial Attacks with Pixel Deflectioncited by 71
  6. 2019Connecting Touch and Vision via Cross-Modal Predictioncited by 66
  7. 2020Distilled Semantics for Comprehensive Scene Understanding from Videoscited by 39
  8. 2020Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensuscited by 8
  9. 2023Self-supervised Hypergraphs for Learning Multiple World Interpretationscited by 8
  10. 2023Multi-Task Hypergraphs for Semi-supervised Learning using Earth Observationscited by 6
  11. 2019Casting Geometric Constraints in Semantic Segmentation as Semi-Supervised Learningcited by 5

Built on by

Not cited yet.