mlsanityData to 7 Oct 2026

Adversarial Masking for Self-Supervised Learning

arXiv 2201.13100 ↗First posted 31 Jan 2022cs.CV cs.LGcited by 78

Not on the map. Why?

Abstract (arXiv)

We propose ADIOS, a masked image model (MIM) framework for self-supervised learning, which simultaneously learns a masking function and an image encoder using an adversarial objective. The image encoder is trained to minimise the distance between representations of the original and that of a masked image. The masking function, conversely, aims at maximising this distance. ADIOS consistently improves on state-of-the-art self-supervised learning (SSL) methods on a variety of tasks and datasets -- including classification on ImageNet100 and STL10, transfer learning on CIFAR10/100, Flowers102 and iNaturalist, as well as robustness evaluated on the backgrounds challenge (Xiao et al., 2021) -- while generating semantically meaningful masks. Unlike modern MIM models such as MAE, BEiT and iBOT, ADIOS does not rely on the image-patch tokenisation construction of Vision Transformers, and can be implemented with convolutional backbones. We further demonstrate that the masks learned by ADIOS are more effective in improving representation learning of SSL methods than masking schemes used in popular MIM models. Code is available at https://github.com/YugeTen/adios.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). Builds on 31 of its 43 references that are in the map. First posted on arXiv 31 Jan 2022.

Builds on

31 of 43 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  7. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  8. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  9. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  10. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  11. 2022A ConvNet for the 2020scited by 3,545
  12. 2020Exploring Simple Siamese Representation Learningcited by 2,853
19 more
  1. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  2. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  3. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  4. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  5. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  6. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  7. 2019Contrastive Multiview Codingcited by 1,297
  8. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 891
  9. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 359
  10. 2020SCAN: Learning to Classify Images without Labelscited by 351
  11. 2020Noise or Signal: The Role of Image Backgrounds in Object Recognitioncited by 342
  12. 2020Whitening for Self-Supervised Representation Learningcited by 278
  13. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  14. 2021Solo-learn: A Library of Self-supervised Methods for Visual Representation Learningcited by 116
  15. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  16. 2019Faster AutoAugment: Learning Augmentation Strategies using Backpropagationcited by 96
  17. 2020Viewmaker Networks: Learning Views for Unsupervised Representation Learningcited by 48
  18. 2021Augmenting Convolutional networks with attention-based aggregationcited by 29
  19. 2021Contrastive Representation Learning with Trainable Augmentation Channelcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 16; 2023: 26; 2024: 19; 2025: 8; 2026: 9.

78 papers.

Sort:

By area:

  1. 2022SemMAE: Semantic-Guided Masking for Learning Masked Autoencoderscited by 113
  2. 2022Masked Frequency Modeling for Self-Supervised Visual Pre-Trainingcited by 70
  3. 2023Hard Patches Mining for Masked Image Modelingcited by 56
  4. 2022Understanding Masked Image Modeling via Learning Occlusion Invariant Featurecited by 50
  5. 2023Understanding Masked Autoencoders via Hierarchical Latent Variable Modelscited by 39
  6. 2023Mixed Autoencoder for Self-supervised Visual Representation Learningcited by 38
  7. 2023Anatomical Invariance Modeling and Semantic Alignment for Self-supervised Learning in 3D Medical Image Analysiscited by 25
  8. 2022Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Workscited by 24
  9. 2024MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embeddingcited by 22
  10. 2022Extreme Masking for Learning Instance and Distributed Visual Representationscited by 21
  11. 2023CL-MAE: Curriculum-Learned Masked Autoencoderscited by 21
  12. 2024FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learningcited by 21
38 more
  1. 2023Improving Masked Autoencoders by Learning Where to Maskcited by 20
  2. 2024Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learningcited by 19
  3. 2022Swin MAE: Masked Autoencoders for Small Datasetscited by 17
  4. 2023Learning Common Rationale to Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problemscited by 14
  5. 2024Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-trainingcited by 14
  6. 2023Masked Modeling for Self-supervised Representation Learning on Vision and Beyondcited by 13
  7. 2024Efficient Vision-Language Pre-training by Cluster Maskingcited by 13
  8. 2023Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimickingcited by 12
  9. 2024Harnessing Massive Satellite Imagery with Efficient Masked Image Modelingcited by 12
  10. 2022Adapting Self-Supervised Vision Transformers by Probing Attention-Conditioned Masking Consistencycited by 11
  11. 2023Pre-training with Random Orthogonal Projection Image Modelingcited by 11
  12. 2023Ignorance is Bliss: Robust Control via Information Gatingcited by 10
  13. 2024AnatoMask: Enhancing Medical Image Segmentation with Reconstruction-guided Self-maskingcited by 10
  14. 2024DMT-JEPA: Discriminative Masked Targets for Joint-Embedding Predictive Architecturecited by 8
  15. 2024ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoderscited by 8
  16. 2026SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Modelcited by 7
  17. 2022UnICLAM:Contrastive Representation Learning with Adversarial Masking for Unified and Interpretable Medical Vision Question Answeringcited by 6
  18. 2022GEDI: GEnerative and DIscriminative Training for Self-Supervised Learningcited by 6
  19. 2022Disjoint Masking with Joint Distillation for Efficient Masked Image Modelingcited by 6
  20. 2022Masked Contrastive Representation Learningcited by 5
  21. 2023Bootstrap Masked Visual Modeling via Hard Patches Miningcited by 5
  22. 2024An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Trainingcited by 4
  23. 2024Progressive Proxy Anchor Propagation for Unsupervised Semantic Segmentationcited by 4
  24. 2022Adversarial Pretraining of Self-Supervised Deep Networks: Past, Present and Futurecited by 3
  25. 2022Pretraining ECG Data with Adversarial Masking Improves Model Generalizability for Data-Scarce Taskscited by 3
  26. 2022Homomorphic Self-Supervised Learningcited by 3
  27. 2023Aerial Image Object Detection With Vision Transformer Detector (ViTDet)cited by 3
  28. 2023Distributed Traffic Synthesis and Classification in Edge Networks: A Federated Self-supervised Learning Approachcited by 3
  29. 2023Constructive Assimilation: Boosting Contrastive Learning Performance through View Generation Strategiescited by 3
  30. 2025AutoSSVH: Exploring Automated Frame Sampling for Efficient Self-Supervised Video Hashingcited by 3
  31. 2025Self-Guided Masked Autoencodercited by 3
  32. 2023Remote Sensing Scene Classification with Masked Image Modeling (MIM)cited by 2
  33. 2023DPPMask: Masked Image Modeling with Determinantal Point Processescited by 2
  34. 2023Feature-Suppressed Contrast for Self-Supervised Food Pre-trainingcited by 2
  35. 2023Contrastive Learning for Lane Detection via cross-similaritycited by 2
  36. 2023Enhancing Representations through Heterogeneous Self-Supervised Learningcited by 2
  37. 2024Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learningcited by 2
  38. 2024Fine-tuning a Multiple Instance Learning Feature Extractor with Masked Context Modelling and Knowledge Distillationcited by 2

50 most cited of 78 All 78 (JSON)