mlsanityData to 7 Oct 2026

On the Intrinsic Dimensionality of Image Representations

arXiv 1803.09672 ↗First posted 26 Mar 2018cs.CV stat.MLcited by 57

Not on the map. Why?

Abstract (arXiv)

This paper addresses the following questions pertaining to the intrinsic dimensionality of any given image representation: (i) estimate its intrinsic dimensionality, (ii) develop a deep neural network based non-linear mapping, dubbed DeepMDS, that transforms the ambient representation to the minimal intrinsic space, and (iii) validate the veracity of the mapping through image matching in the intrinsic space. Experiments on benchmark image datasets (LFW, IJB-C and ImageNet-100) reveal that the intrinsic dimensionality of deep neural network representations is significantly lower than the dimensionality of the ambient features. For instance, SphereFace's 512-dim face representation and ResNet's 512-dim image representation have an intrinsic dimensionality of 16 and 19 respectively. Further, the DeepMDS mapping is able to obtain a representation of significantly lower dimensionality while maintaining discriminative ability to a large extent, 59.75% TAR @ 0.1% FAR in 16-dim vs 71.26% TAR in 512-dim on IJB-C and a Top-1 accuracy of 77.0% at 19-dim vs 83.4% at 512-dim on ImageNet-100.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 11; 2023: 10; 2024: 7; 2025: 11; 2026: 11.

57 papers.

Sort:

By area:

  1. 2021The Intrinsic Dimension of Images and Its Impact on Learningcited by 307
  2. 2022Matryoshka Representation Learningcited by 268
  3. 2022Assessing the State of Self-Supervised Human Activity Recognition using Wearablescited by 63
  4. 2024Breaking the Curse of Dimensionality: Diffusion Models Efficiently Learn Low-Dimensional Distributionscited by 53
  5. 2023Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvementcited by 49
  6. 2023Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionalitycited by 44
  7. 2022When do GANs replicate? On the choice of dataset sizecited by 34
  8. 2021Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networkscited by 32
  9. 2024Diffusion Model for Data-Driven Black-Box Optimizationcited by 24
  10. 2022Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Powercited by 23
  11. 2025Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modelingcited by 18
  12. 2024The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Imagescited by 13
38 more
  1. 202550 Years of Automated Face Recognitioncited by 13
  2. 2022Topology and geometry of data manifold in deep learningcited by 12
  3. 2022Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networkscited by 12
  4. 2021Biometric Template Protection for Neural-Network-based Face Recognition Systems: A Survey of Methods and Evaluation Techniquescited by 11
  5. 2023Data Representations' Study of Latent Image Manifoldscited by 11
  6. 2024LDReg: Local Dimensionality Regularized Self-Supervised Learningcited by 11
  7. 2025Measuring the Intrinsic Dimension of Earth Representationscited by 10
  8. 2023Benchmarking fixed-length Fingerprint Representations across different Embedding Sizes and Sensor Typescited by 8
  9. 2025Geometry of Decision Making in Language Modelscited by 8
  10. 2021Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classificationcited by 7
  11. 2023Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic Dimensioncited by 7
  12. 2023A Latent Fingerprint in the Wild Databasecited by 7
  13. 2021Feature Fusion Methods for Indexing and Retrieval of Biometric Data: Application to Face Recognition with Privacy Protectioncited by 5
  14. 2022A Manifold Two-Sample Test Study: Integral Probability Metric with Neural Networkscited by 5
  15. 2022FONDUE: an algorithm to find the optimal dimensionality of the latent representations of variational autoencoderscited by 5
  16. 2023Deep neural networks architectures from the perspective of manifold learningcited by 5
  17. 2024Mobile Contactless Palmprint Recognition: Use of Multiscale, Multimodel Embeddingscited by 5
  18. 2022Overparameterization Improves StyleGAN Inversioncited by 4
  19. 2021Canonical Face Embeddingscited by 3
  20. 2023Linear Regression on Manifold Structured Data: the Impact of Extrinsic Geometry on Solutionscited by 3
  21. 2025Adjustment for Confounding using Pre-Trained Representationscited by 3
  22. 2021Intrinisic Gradient Compression for Federated Learningcited by 2
  23. 2025Non-Adaptive Adversarial Face Generationcited by 2
  24. 2026Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Modelscited by 2
  25. 2024Subject-Independent Deep Architecture for EEG-based Motor Imagery Classificationcited by 1
  26. 2024Pre-processing and Compression: Understanding Hidden Representation Refinement Across Imaging Domains via Intrinsic Dimensioncited by 1
  27. 2025Geometry-Guided Adversarial Prompt Detection via Curvature and Local Intrinsic Dimensioncited by 1
  28. 2025Dataset-Adaptive Dimensionality Reductioncited by 1
  29. 2025Diagonally-Weighted Generalized Method of Moments Estimation for Gaussian Mixture Modelingcited by 1
  30. 2025MOCLIP: A Foundation Model for Large-Scale Nanophotonic Inverse Designcited by 1
  31. 2026Multi-Subspace Multi-Modal Modeling for Diffusion Models: Estimation, Convergence and Mixture of Expertscited by 1
  32. 2026High-dimensional Semi-supervised Classification via the Fermat Distancecited by 1
  33. 2026ShuffleFlow: Scalable Posterior Inference for Bayesian Inverse Imagingcited by 1
  34. 2022RENs: Relevance Encoding Networkscited by 0
  35. 2022Dimensionality of datasets in object detection networkscited by 0
  36. 2023Manifold Regularization for Memory-Efficient Training of Deep Neural Networkscited by 0
  37. 2023Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networkscited by 0
  38. 2025Breaking the Curse of Dimensionality: On the Stability of Modern Vector Retrievalcited by 0

50 most cited of 57 All 57 (JSON)