Papers
Topics
Authors
Recent
Search
2000 character limit reached

Rotation and Translation Invariant Representation Learning with Implicit Neural Representations

Published 27 Apr 2023 in cs.CV and cs.AI | (2304.13995v2)

Abstract: In many computer vision applications, images are acquired with arbitrary or random rotations and translations, and in such setups, it is desirable to obtain semantic representations disentangled from the image orientation. Examples of such applications include semiconductor wafer defect inspection, plankton microscope images, and inference on single-particle cryo-electron microscopy (cryo-EM) micro-graphs. In this work, we propose Invariant Representation Learning with Implicit Neural Representation (IRL-INR), which uses an implicit neural representation (INR) with a hypernetwork to obtain semantic representations disentangled from the orientation of the image. We show that IRL-INR can effectively learn disentangled semantic representations on more complex images compared to those considered in prior works and show that these semantic representations synergize well with SCAN to produce state-of-the-art unsupervised clustering results.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (65)
  1. Image generators with conditionally-independent pixel synthesis. arXiv preprint arXiv:2011.13775, 2020.
  2. Explicitly disentangling image content from translation and rotation with spatial-VAE. Neural Information Processing Systems, 2019.
  3. Signature verification using a “siamese” time delay neural network. Neural Information Processing Systems, 1993.
  4. Extracting speaker-specific information with a regularized siamese deep network. Neural Information Processing Systems, 2011.
  5. Isolating sources of disentanglement in variational autoencoders. Neural Information Processing Systems, 2018.
  6. A simple framework for contrastive learning of visual representations. International Conference on Machine Learning, 2020.
  7. Exploring simple siamese representation learning. Computer Vision and Pattern Recognition, 2021.
  8. InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets. Neural Information Processing Systems, 2016.
  9. Learning continuous image representation with local implicit image function. Computer Vision and Pattern Recognition, 2021.
  10. Comon, P. Independent component analysis, a new concept? Signal Processing, 36(3):287–314, 1994.
  11. Theoretical Statistics. Chapman and Hall, 1979.
  12. Randaugment: Practical automated data augmentation with a reduced search space. Computer Vision and Pattern Recognition Workshops, 2020.
  13. Nearest neighbor matching for deep clustering. Computer Vision and Pattern Recognition, 2021.
  14. Vector neurons: A general framework for so(3)-equivariant networks. Computer Vision and Pattern Recognition, 2021.
  15. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552, 2017.
  16. Rotation-invariant convolutional neural networks for galaxy morphology prediction. Monthly Notices of the Royal Astronomical Society, 450(2):1441–1459, 2015.
  17. Generative models as distributions of functions. Artificial Intelligence and Statistics, 2022.
  18. Temporal cycle-consistency learning. Computer Vision and Pattern Recognition, 2019.
  19. Leveraging shape completion for 3d siamese tracking. Computer Vision and Pattern Recognition, 2019.
  20. Bootstrap your own latent - a new approach to self-supervised learning. Neural Information Processing Systems, 2020.
  21. Hypernetworks. International Conference on Learning Representations, 2017.
  22. Deep residual learning for image recognition. Computer Vision and Pattern Recognition, 2016.
  23. Momentum contrast for unsupervised visual representation learning. Computer vision and Pattern Recognition, 2020.
  24. beta-VAE: Learning basic visual concepts with a constrained variational framework. International Conference on Learning Representations, 2017.
  25. Learning deep representations by mutual information estimation and maximization. International Conference on Learning Representations, 2019.
  26. Independent component analysis: algorithms and applications. Neural Networks, 13(4):411–430, 2000.
  27. Deep subspace clustering networks. Neural Information Processing Systems, 2017.
  28. A style-based generator architecture for generative adversarial networks. Computer Vision and Pattern Recognition, 2019.
  29. Alias-free generative adversarial networks. Neural Information Processing Systems, 2021.
  30. Variational inference of disentangled latent concepts from unlabeled observations. International Conference on Learning Representations, 2018.
  31. Contrastive clustering. American Association for Artificial Intelligence, 35(10):8547–8555, 2021.
  32. β𝛽\betaitalic_β-subunit binding is sufficient for ligands to open the integrin αIIb⁢β3subscript𝛼IIbsubscript𝛽3\alpha_{\text{IIb}}\beta_{3}italic_α start_POSTSUBSCRIPT IIb end_POSTSUBSCRIPT italic_β start_POSTSUBSCRIPT 3 end_POSTSUBSCRIPT headpiece. Journal of Biological Chemistry, 291(9):4537–4546, 2015.
  33. Galaxy Zoo: Morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey. Monthly Notices of the Royal Astronomical Society, 389(3):1179–1189, 2008.
  34. Relighting images in the wild with a self-supervised siamese auto-encoder. Winter Conference on Applications of Computer Vision, 2020.
  35. Disentangling factors of variations using few labels. International Conference on Learning Representations, 2020.
  36. Nerf: Representing scenes as neural radiance fields for view synthesis. European Conference on Computer Vision, 2020.
  37. Self-supervised learning of pretext-invariant representations. Computer Vision and Pattern Recognition, June 2020.
  38. Unsupervised object representation learning using translation and rotation group equivariant VAE. Neural Information Processing Systems, 2022.
  39. WHOI-plankton- a large scale fine grained visual recognition benchmark dataset for plankton classification. arXiv:1510.00745, 2015.
  40. Random features for large-scale kernel machines. Neural Information Processing Systems, 2007.
  41. Time-contrastive networks: Self-supervised learning from video. International Conference in Robotics and Automation, 2018.
  42. Decomposed eigenface for face recognition under various lighting conditions. Computer Vision and Pattern Recognition, 2001.
  43. You never cluster alone. Neural Information Processing Systems, 2021.
  44. Deforming autoencoders: Unsupervised disentangling of shape and appearance. European Conference on Computer Vision, 2018.
  45. Scene representation networks: Continuous 3d-structure-aware neural scene representations. Neural Information Processing Systems, 2019.
  46. Implicit neural representations with periodic activation functions. Neural Information Processing Systems, 2020.
  47. Stanley, K. O. Compositional pattern producing networks: A novel abstraction of development. Genetic Programming and Evolvable Machines, 8(2):131–162, 2007.
  48. Fourier features let networks learn high frequency functions in low dimensional domains. Neural Information Processing Systems, 2020.
  49. Learning deep representations for graph clustering. American Association for Artificial Intelligence, 2014.
  50. Disentangled representation learning GAN for pose-invariant face recognition. Computer Vision and Pattern Recognition, 2017.
  51. Representation learning with contrastive predictive coding. arXiv:1807.03748, 2018.
  52. Scan: Learning to classify images without labels. European Conference on Computer Vision, 2020.
  53. Wang, C.-H. Recognition of semiconductor defect patterns using spatial filtering and spectral clustering. Expert Systems with Applications, 34(3):1914–1923, 2008.
  54. Wafer map defect pattern recognition using rotation-invariant features. IEEE Transactions on Semiconductor Manufacturing, 32(4):596–604, 2019.
  55. Defect pattern recognition on wafers using convolutional neural networks. Quality and Reliability Engineering International, 36(4):1245–1257, 2020.
  56. Unsupervised learning of visual representations using videos. International Conference on Computer Vision, 2015.
  57. Wafer map failure pattern recognition and similarity ranking for large-scale data sets. IEEE Transactions on Semiconductor Manufacturing, 28:1–12, 2015.
  58. Unsupervised feature learning via non-parametric instance discrimination. Computer Vision and Pattern Recognition, 2018.
  59. Unsupervised deep embedding for clustering analysis. International Conference on Machine Learning, 2016.
  60. Decoupled contrastive learning. European Conference on Computer Vision, 2022.
  61. Learning a self-expressive network for subspace clustering. Computer Vision and Pattern Recognition, 2021.
  62. Bagging based plankton image classification. International Conference on Image Processing, 2009.
  63. CryoDRGN: Reconstruction of heterogeneous cryo-EM structures using neural networks. Nature Methods, 18(2):176–185, 2021.
  64. Occlusion-aware siamese network for human pose estimation. European Conference on Computer Vision, 2020.
  65. Deep adversarial subspace clustering. Computer Vision and Pattern Recognition, 2018.
Citations (3)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up