mlsanityData to 14 Oct 2026

What Images are More Memorable to Machines?

arXiv 2211.07625 ↗First posted 14 Nov 2022cs.CV cs.AI cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

This paper studies the problem of measuring and predicting how memorable an image is to pattern recognition machines, as a path to explore machine intelligence. Firstly, we propose a self-supervised machine memory quantification pipeline, dubbed ``MachineMem measurer'', to collect machine memorability scores of images. Similar to humans, machines also tend to memorize certain kinds of images, whereas the types of images that machines and humans memorize are different. Through in-depth analysis and comprehensive visualizations, we gradually unveil that``complex" images are usually more memorable to machines. We further conduct extensive experiments across 11 different machines (from linear classifiers to modern ViTs) and 9 pre-training methods to analyze and understand machine memory. This work proposes the concept of machine memorability and opens a new research direction at the interface between machine memory and visual data.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 50 of its 94 references that are in the map. First posted on arXiv 14 Nov 2022.

Builds on

50 of 94 references.

References · 50

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  6. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  8. 2017Mask R-CNNcited by 7,277
  9. 2016Densely Connected Convolutional Networkscited by 6,720
  10. 2017On Calibration of Modern Neural Networkscited by 4,960
  11. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  12. 2014Going Deeper with Convolutionscited by 4,241
38 more
  1. 2016Wide Residual Networkscited by 3,070
  2. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  3. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  4. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  5. 2017Non-local Neural Networkscited by 2,293
  6. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  7. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  8. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  9. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  10. 2017Random Erasing Data Augmentationcited by 1,239
  11. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,066
  12. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  13. 2017A Closer Look at Memorization in Deep Networkscited by 942
  14. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  15. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  16. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
  17. 2018An Empirical Study of Example Forgetting during Deep Neural Network Learningcited by 678
  18. 2014Neural Turing Machinescited by 644
  19. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 497
  20. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  21. 2019Does Learning Require Memorization? A Short Tale about a Long Tailcited by 460
  22. 2017NIMA: Neural Image Assessmentcited by 389
  23. 2021XCiT: Cross-Covariance Image Transformerscited by 338
  24. 2021Skillful Precipitation Nowcasting using Deep Generative Models of Radarcited by 311
  25. 2019GANalyze: Toward Visual Definitions of Cognitive Image Propertiescited by 193
  26. 2020Memory-augmented Dense Predictive Coding for Video Representation Learningcited by 137
  27. 2015Ask Me Anything: Dynamic Memory Networks for Natural Language Processingcited by 117
  28. 2020Convolutional Networks with Dense Connectivitycited by 98
  29. 2015Posterior calibration and exploratory analysis for natural language processing modelscited by 76
  30. 2021What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?cited by 63
  31. 2021People construct simplified mental representations to plancited by 47
  32. 2022You Only Cut Once: Boosting Data Augmentation with a Single Cutcited by 22
  33. 2018AMNet: Memorability Estimation with Attentioncited by 16
  34. 2019Is Image Memorability Prediction Solved?cited by 9
  35. 2019Empirical Study of Easy and Hard Examples in CNN Trainingcited by 9
  36. 2021Memorability: An image-computable measure of information utilitycited by 8
  37. 2022CropMix: Sampling a Rich Input Distribution via Multi-Scale Croppingcited by 8
  38. 2018Understanding and Predicting the Memorability of Outdoor Natural Scenescited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 3; 2026: 1.

5 papers.

  1. 2025SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-trainingcited by 672
  2. 2025Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-trainingcited by 23
  3. 2023What do larger image classifiers memorise?cited by 6
  4. 2025From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Imagescited by 2
  5. 2026Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoningcited by 0