mlsanityData to 7 Oct 2026

Inverse Problems Leveraging Pre-trained Contrastive Representations

arXiv 2110.07439 ↗First posted 14 Oct 2021cs.LG cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

We study a new family of inverse problems for recovering representations of corrupted data. We assume access to a pre-trained representation learning network R(x) that operates on clean images, like CLIP. The problem is to recover the representation of an image R(x), if we are only given a corrupted version A(x), for some known forward operator A. We propose a supervised inversion method that uses a contrastive objective to obtain excellent representations for highly corrupted images. Using a linear probe on our robust representations, we achieve a higher accuracy than end-to-end supervised baselines when classifying images with various types of distortions, including blurring, additive noise, and random pixel masking. We evaluate on a subset of ImageNet and observe that our method is robust to varying levels of distortion. Our method outperforms end-to-end baselines even with a fraction of the labeled data in a wide range of forward operators.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 36 of its 46 references that are in the map. First posted on arXiv 14 Oct 2021.

Builds on

36 of 46 references.

References · 36

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  7. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  8. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  9. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  10. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  11. 2020Supervised Contrastive Learningcited by 2,803
  12. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
24 more
  1. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  2. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  3. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  4. 2019Contrastive Multiview Codingcited by 1,297
  5. 2019Contrastive Representation Distillationcited by 734
  6. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 672
  7. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
  8. 2020Robust Pre-Training by Adversarial Contrastive Learningcited by 144
  9. 2020Adversarial Self-Supervised Contrastive Learningcited by 138
  10. 2020Intriguing Properties of Contrastive Lossescited by 129
  11. 2018Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networkscited by 120
  12. 2017A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortionscited by 107
  13. 2020COVID-19 Image Data Collectioncited by 100
  14. 2019Invertible generative models for inverse problems: mitigating representation error and dataset biascited by 93
  15. 2020Contrastive Learning with Adversarial Examplescited by 91
  16. 2020Understanding Self-supervised Learning with Dual Deep Networkscited by 62
  17. 2021Measuring Robustness in Deep Learning Based Compressive Sensingcited by 53
  18. 2017Google's Cloud Vision API Is Not Robust To Noisecited by 37
  19. 2018Modeling Sparse Deviations for Compressed Sensing using Generative Modelscited by 33
  20. 2017On Classification of Distorted Images with Deep Convolutional Neural Networkscited by 26
  21. 2018CURE-OR: Challenging Unreal and Real Environments for Object Recognitioncited by 18
  22. 2019Fast and Provable ADMM for Learning with Generative Priorscited by 18
  23. 2018Task-Aware Compressed Sensing with Generative Adversarial Networkscited by 17
  24. 2019Inference with Deep Generative Priors in High Dimensionscited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 0; 2024: 1; 2025: 0; 2026: 1.

7 papers.

  1. 2021Extract Free Dense Labels from CLIPcited by 580
  2. 2022Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistencycited by 246
  3. 2022Online Deep Equilibrium Learning for Regularization by Denoisingcited by 22
  4. 2022Embed and Emulate: Learning to estimate parameters of dynamical systems with uncertainty quantificationcited by 5
  5. 2022Feedback is Needed for Retakes: An Explainable Poor Image Notification Framework for the Visually Impairedcited by 0
  6. 2024End-to-End Mineral Exploration with Artificial Intelligence and Ambient Noise Tomographycited by 0
  7. 2026Distilling Vision Transformers for Distortion-Robust Representation Learningcited by 0