Publications

Selected Publications are listed below, see my Google Scholar for a comprehensive and up to date list.

These papers are possible because of a wonderful set of collaborators, mentors, and students over the years: Jay Thiagarajan, Timo Bremer, Pavan Turaga, Suhas Lohit, Bhavya Kailkhura, Hyojin Kim, Shusen Liu, Brian Spears, Tammy Ma, Anuj Srivastava, Kyle Champley, Aditya Mohan, Vivek Narayanaswamy, Suren Jayasuriya, Irene Kim, Kowshik Thopalli, Albert Reed, Tejas Gokhale, Harsh Bhatia, Ankita Shukla, Matt Olson, Rakshith Subramanyam

Preprints and Working Papers

  1. Revisiting Inlier and Outlier Specification for Improved Out-of-Distribution Detection (2022) [arXiv]

2023

  1. (new!) Improving Diversity with Adversarially Learned Transformations for Domain Generalization.
    Gokhale, T., Anirudh, R., Thiagarajan, J. J., Kailkhura, B., Baral, C. and Yang, Y.,
    In WACV 2023 [paper] [code]
  2. (new!) Contrastive Knowledge-Augmented Meta-Learning for Few-Shot Classification.
    Subramanyam, R., Heimann, M., Thathachar, J., Anirudh, R., & Thiagarajan, J. J.
    In WACV 2023 [paper] [code]

2022

  1. (new!) Single Model Uncertainty Estimation via Stochastic Data Centering
    Thiagarajan*, J.J., Anirudh*, R., Narayanaswamy, V. and Bremer, P.T., (*=equal)
    Spotlight at NeurIPS 2022 [paper]
  2. (new!) Out of Distribution Detection using Neural Network Anchoring
    Anirudh, R., and Thiagarajan, J. J.,
    In ACML 2022 [paper    ] [code]
  3. Improved Medical Out-of-Distribution Detectors For Modality and Semantic Shifts
    Narayanaswamy, V., Mubaraka, Y., Anirudh, R., Rajan, D., Spanias, A., Thiagarajan, J. J.,
    in     ICML2022 Workshop on Principles of Distribution Shift [paper]
  4. Data-Efficient Scientific Design Optimization with Neural Network Surrogates,
    Thiagarajan, J. J., Anirudh, R., Mubaraka, Y., Kim, I., Bremer, PT., Peterson, J. L., Spears, B.,
    in     ICML2022 Workshop on Adaptive Experimental Design and Active Learning in the Real World [paper]
  5. Accurate Calibration of Agent-based Epidemiological Models with Neural Network Surrogates,
    Anirudh, R., Thiagarajan, J. J., Bremer, P. T., Germann, T. C., Del Valle, S. Y., & Streitz, F. H.,
    in     ICML2022 Workshop on Healthcare AI and COVID-19 [paper]
  6. Machine Learning-Powered Mitigation Policy Optimization in Epidemiological Models,
    Thiagarajan, J. J., Anirudh, R., Bremer, P. T., Germann, T. C., Del Valle, S. Y., & Streitz, F. H.,
    in     ICML2022 Workshop on Healthcare AI and COVID-19 [paper]
  7. Predicting the Generalization Gap in Deep Models using Anchoring,
    Narayanaswamy, V., Anirudh, R., Kim, I., Mubaraka, Y., Spanias, A., Thiagarajan, J. J.,
    in     ICASSP 2022. [paper]
  8. Sparsity Improves Unsupervised Attribute Discovery in StyleGAN,
    Liu, S., Anirudh, R., Thiagarajan, J. J., Bremer, P. T.,
    in     ICASSP 2022. [paper]

2021

  1. Unsupervised Attribute Alignment for Characterizing Distribution Shift.
    Olson, M.L., Liu, S., Anirudh, R., Thiagarajan, J. J., Wong, W. K. and Bremer, P. T.,
    In     NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications. [paper]
  2. Geometric Priors for Scientific Generative Models in Inertial Confinement Fusion.
    Shukla, A., Anirudh, R., Kur, E., Thiagarajan, J. J., Bremer, P. T., Spears, B.K., Ma, T. & Turaga, P.,
    In     NeurIPS 2021 Workshop on ML for Physical Sciences (ML4PS) [paper]
  3. Data-Driven Estimation of Temporal-Sampling Errors in Unsteady Flows,
    Bhatia, H., Petruzza, S. N., Anirudh, R., Gyulassy, A. G., Kirby, R. M., Pascucci, V., & Bremer, P. T.,
    In ISVC, 2021.
  4. Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fields,
    Reed, A. W., Kim, H., Anirudh, R., Mohan, K. A., Champley, K., Kang, J., & Jayasuriya, S.,
    ICCV, 2021. [paper]
  5. MR-GAN: Manifold Regularized Generative Adversarial Networks for Scientific Data.
    Li, Q., Kailkhura, B., Anirudh, R., Zhang, J., Zhou, Y., Liang, Y., Han, T.Y.J. & Varshney, P.K.,
    In SIAM Mathematics of Data Science (    SIMODS), 2021. [paper]
  6. Machine Learning Methods for Autism Spectrum Disorder Classification.
    Anirudh, R., and Thiagarajan, J. J.,
    Book chapter in Neural Engineering Techniques for Autism Spectrum Disorder (Editors: A. S. El-Baz & J. Suri, Publisher: Elsevier), 2021.
  7. MARGIN: Uncovering Deep Neural Networks using Graph Signal Analysis,
    Anirudh, R.*, Thiagarajan, J. J.*, Sridhar, R., Bremer, P. T.,
    in     Frontiers in Big Data-Machine Learning and Artificial Intelligence, May 2021. [arxiv preprint] [paper] (* = equal contribution)
  8. Attribute-guided Adversarial Training for Robustness to Natural Perturbations,
    Gokhale, T., Anirudh, R., Kailkhura, B., Thiagarajan, J. J., Baral, C., Yang, Y.,
    In     AAAI 2021. [paper][arXiv preprint]
  9. Accurate and Robust Feature Importance Estimation under Distribution Shifts,
    Thiagarajan, J. J., Narayanaswamy, V., Anirudh, R., Bremer, P. T., Spanias, A.,
    In     AAAI 2021. [paper][arXiv preprint]
  10. Recovering Trajectories of Unmarked Joints in 3D Human Actions Using Latent Space Optimization,
    Lohit, S., Anirudh, R., Turaga, P.,
    In     WACV 2021. [pdf]
  11. Generative Patch Priors for Practical Compressive Image Recovery,
    Anirudh, R., Lohit, S., Turaga, P.,
    In     WACV 2021. [pdf] [github] [press release] Best Paper Honorable Mention Award!

2020

  1. Designing Accurate Emulators for Scientific Processes using Calibration-Driven Deep Models,
    Thiagarajan, J. J., Venkatesh, B., Anirudh, R., Bremer, P. T., Gaffney, J., Anderson, G., Spears, B.K.,
    In     Nature Communications, [paper] Featured in editor's picks (link)
  2. Unsupervised Audio Source Separation using Generative Priors,
    Narayanaswamy, V., Thiagarajan, J.J., Anirudh, R., & Spanias, A.,
    In     Interspeech 2020. [paper] [code]
  3. Uncovering Interpretable Relationships in High-Dimensional Scientific Data Through Function Preserving Projections,
    Liu, S., Anirudh, R., Thiagarajan, J. J., & Bremer, P. T., 
    In  Machine Learning: Science and Technology [paper] [github]
  4. Improved Surrogates in Inertial Confinement Fusion with Manifold and Cycle Consistencies,
    Anirudh, R., Thiagarajan, J. J., Bremer, P. T., Spears, B.K.,
    In Proc. of National Academy of Sciences (    PNAS) [arXiv] [paper] [github] [Slides]
  5. MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking,
    Anirudh, R., Thiagarajan, J. J., Kailkhura, B., Bremer, P. T.,
    In International Journal of Computer Vision (    IJCV) Special Issue on GANs, [paper][arXiv][earlier versions]
  6. Manifold Learning,
    Turaga, P., Anirudh, R., Chellappa, R.,
    in Computer Vision. (editor: Katsushi Ikeuchi) Springer, Feb 2020. [Chapter on Springer]
  7. Rate-Invariant Autoencoding of Time-Series,
    Koneripalli, K., Lohit, S., Anirudh, R., & Turaga, P.,
    in     ICASSP 2020. [preprint] [published version]

2019

  1. Bootstrapping graph convolutional neural networks for autism spectrum disorder classification,
    Anirudh, R., & Thiagarajan, J. J.,
    in ICASSP 2019. [arXiv preprint]
  2. Unsupervised Dimension Selection using a Blue Noise Spectrum.
    Thiagarajan, J. J., Anirudh, R., Sridhar, R., & Bremer, P. T.,
    in ICASSP 2019. [arXiv preprint].
  3. Understand Deep Neural Networks through Input Uncertainties,
    Thiagarajan, J. J., Kim, I., Anirudh, R., & Bremer, P. T.,
    in ICASSP 2019 (Oral). [arXiv preprint]
  4. Multiple Subspace Alignment Improves Domain Adaptation,
    Thopalli, K., Anirudh, R., Thiagarajan, J. J., Turaga, P.,
    in ICASSP 2019. [arXiv preprint]
  5. Extreme Few-view CT Reconstruction using Deep Inference,
    H. Kim et al.,
    Deep Inverse NeurIPS 2019 Workshop. [paper]
  6. Improving Limited Angle CT Reconstruction with a Robust GAN Prior,
    R. Anirudh et al.,
    Deep Inverse NeurIPS 2019 Workshop. [paper]
  7. Exploring Generative Physics Models with Scientific Priors in Inertial Confinement Fusion,
    R. Anirudh et al.,
    Machine Learning for Physical Sciences Workshop at NeurIPS 2019. [paper]
  8. Designing Deep Inverse Models for History Matching in Reservoir Simulations,
    V. S. Narayanaswamy et al.,
    Machine Learning for Physical Sciences Workshop at NeurIPS 2019 [paper]
  9. Modeling Human Brain Connectomes using Structured Neural Networks,
    U. S. Shathamallu, et al.
    Graph Representation Learning Workshop at NeurIPS 2019. [paper]


<= 2018

  1. Thiagarajan, J.J., Jain, N., Anirudh, R., et al., Bootstrapping Parameter Space Exploration for Fast Tuning, to appear in ICS 2018.
  2. Anirudh, R., Kim, H., Thiagarajan, J. J., Mohan, K.A., Champley, K., Bremer, T., Lose The Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion,  [pdf] [supplementary material]. Spotlight talk (given to ~7% of 3300 submissions) in CVPR, 2018. 
  3. Thiagarajan, J.J., Anirudh, R.,  et al. PADDLE: Performance Analysis using a Data-driven Learning Environment. to appear in IPDPS 2018.
  4. Anirudh, R., Turaga, P., & Srivastava, A., Optimization Problems Associated with Manifold-Valued Curves with Applications in Computer Vision. In Convex Optimization Methods in Imaging Science, 2017. [Springer].
  5. Marathe, A., Anirudh, R., et al., Performance Modeling under Resource Constraints Using Deep Transfer Learning,SC 2017. [pdf]
  6. Anirudh, R., Kailkhura, B., Thiagarajan, J. J., Bremer, T., Poisson Disk Sampling on the Grassmannnian: Applications in Subspace Optimization, CVPR Workshops 2017. [pdf]
  7. Anirudh, R., Turaga, P., Su, J., & Srivastava, A., Elastic Functional Coding of Riemannian Trajectories. Accepted T-PAMI, 2016. -- 2016 Impact Factor: 8.329 [arXiv] [IEEE Xplore] [github]
  8. Anirudh, R., & Turaga, P., Geometry-based symbolic approximation for fast sequence matching on manifolds. Accepted at IJCV, 2015 -- 2015 Impact Factor: 4.275 [arXiv] [Springer]
  9. Shroff, N., Anirudh, R., & Chellappa, R., Summarization and search over geometric spaces. In Riemannian Computing in Computer Vision, 2016.[Springer]
  10. Anirudh, R., Masroor, A., & Turaga, P., Diversity promoting online sampling for streaming video summarization, ICIP 2016. [pdf]
  11. Anirudh, R., Thiagarajan, J. J., Bremer, T., & Kim, H., Lung nodule detection using 3D convolutional neural networks trained on weakly labeled data. SPIE Medical Imaging, 2016. [pdf]
  12. Sivakumar, A., Anirudh, R., & Turaga, P., Geometric Compression of Orientation Signals for Fast Gesture Analysis. DCC 2015. [pdf]
  13. Anirudh, R., Turaga, P., Su, J., & Srivastava, A., Elastic functional coding of human actions: From vector-fields to latent variables. CVPR, 2015. [pdf][code]
  14. Anirudh, R., & Turaga, P., Interactively test driving an object detector: Estimating performance on unlabeled data. WACV, 2014.[pdf]
  15. Anirudh, R., Ramamurthy, K., Thiagarajan, J. J., Turaga, P., & Spanias, A.,  A heterogeneous dictionary model for representation and recognition of human actions., ICASSP, 2013. [pdf]
  16. Anirudh, R., Venkataraman, V., Natesan Ramamurthy, K., & Turaga, P., A Riemannian framework for statistical analysis of topological persistence diagrams, CVPR Workshops 2016 [pdf]. [code]
  17. Som, A., Anirudh, R., Wang, Q., & Turaga, P., Riemannian geometric approaches for measuring movement quality, CVPR Workshops 2016 [pdf].
  18. Wang, Q., Anirudh, R., & Turaga, P., Temporal Reflection Symmetry of Human Actions: A Riemannian Analysis, BMVC Workshops 2015. [pdf].
  19. Anirudh, R., Venkataraman, V., & Turaga, P., A Generalized Lyapunov Feature for Dynamical Systems on Riemannian Manifolds, BMVC Workshops 2015 [pdf].
  20. Krzyzaniak, M., Anirudh, R., Venkataraman, V., Turaga, P., & Wei, S. X. Towards realtime measurement of connectedness in human movement. In Proceedings of the 2nd International Workshop on Movement and Computing (MOCO), 2015. [pdf]

Other Unpublished Work

  1. Shape Pattern Recognition using the Euclidean Distance Method, Undergraduate Thesis Project, April 2010. (pdf)
  2. Frequency-Domain Adaptive Noise Cancellation.  (DSP Term Project), Nov 2010. (pdf)
  3. An OpenCV Implementation of Supervised Texture Segmentation Using Gabor Filters. (Digital Image Processing Term Project) April 2011. (pdf)
  4. Validation of the cortical homunculus using functional-MRI. (Biomedical Image Processing Term Project), Jan 2012. (pdf)
  5. ceci n' est pas une code, R. Anirudh, M. Krzyzaniak, A. Faith, S. Lohit, Sep 2015.
    Inspired by the "The Treachery of Images".
    Displayed on the walls of Stauffer-B at Arizona State University. (original pdf) (on display)