no code implementations • 4 Apr 2025 • Sinjini Mitra, Anuj Srivastava, Avipsa Roy, Pavan Turaga
Human mobility analysis at urban-scale requires models to represent the complex nature of human movements, which in turn are affected by accessibility to nearby points of interest, underlying socioeconomic factors of a place, and local transport choices for people living in a geographic region.
no code implementations • 27 Feb 2025 • Jisoo Lee, Tamim Ahmed, Thanassis Rikakis, Pavan Turaga
Specifically, we perform temporal segmentation of video recordings to capture detailed activities during stroke patients' rehabilitation.
no code implementations • 2 Feb 2025 • Eun Som Jeon, Hongjun Choi, Matthew P. Buman, Pavan Turaga
To tackle this problem, knowledge distillation (KD) can be adopted, which is a technique facilitating model compression and transfer learning to generate a smaller model by transferring knowledge from a larger network.
no code implementations • 12 Aug 2024 • Utkarsh Nath, Rajeev Goel, Eun Som Jeon, Changhoon Kim, Kyle Min, Yezhou Yang, Yingzhen Yang, Pavan Turaga
To address the data scarcity associated with 3D assets, 2D-lifting techniques such as Score Distillation Sampling (SDS) have become a widely adopted practice in text-to-3D generation pipelines.
no code implementations • 7 Jul 2024 • Eun Som Jeon, Hongjun Choi, Ankita Shukla, YuAn Wang, Hyunglae Lee, Matthew P. Buman, Pavan Turaga
Also, we apply an annealing strategy in KD for fast saturation and better accommodation from different features, while the knowledge gap between the teachers and student is reduced.
1 code implementation • 7 Jul 2024 • Eun Som Jeon, Rahul Khurana, Aishani Pathak, Pavan Turaga
We introduce a mechanism for integrating features from different teachers and reducing the knowledge gap between teachers and the student, which aids in improving performance.
no code implementations • 21 Mar 2024 • Jinyung Hong, Eun Som Jeon, Changhoon Kim, Keun Hee Park, Utkarsh Nath, Yezhou Yang, Pavan Turaga, Theodore P. Pavlic
Biased attributes, spuriously correlated with target labels in a dataset, can problematically lead to neural networks that learn improper shortcuts for classifications and limit their capabilities for out-of-distribution (OOD) generalization.
1 code implementation • 22 May 2023 • Kowshik Thopalli, Rakshith Subramanyam, Pavan Turaga, Jayaraman J. Thiagarajan
We argue that augmentations utilized by existing methods are insufficient to handle large distribution shifts, and hence propose a new approach SiSTA, which first fine-tunes a generative model from the source domain using a single-shot target, and then employs novel sampling strategies for curating synthetic target data.
no code implementations • 17 May 2023 • Shenyuan Liang, Pavan Turaga, Anuj Srivastava
This paper investigates the challenge of learning image manifolds, specifically pose manifolds, of 3D objects using limited training data.
1 code implementation • CVPR 2023 • Rajhans Singh, Ankita Shukla, Pavan Turaga
With much fewer training parameters and higher representative power, our approach paves the way for broader adoption of INR models for generative modeling tasks in complex domains.
Ranked #6 on
Image Generation
on ImageNet 128x128
no code implementations • 27 Feb 2023 • Eun Som Jeon, Hongjun Choi, Ankita Shukla, Pavan Turaga
AMD loss uses the angular distance between positive and negative features by projecting them onto a hypersphere, motivated by the near angular distributions seen in many feature extractors.
1 code implementation • 8 Nov 2022 • Hongjun Choi, Eun Som Jeon, Ankita Shukla, Pavan Turaga
Mixup is a popular data augmentation technique based on creating new samples by linear interpolation between two given data samples, to improve both the generalization and robustness of the trained model.
1 code implementation • 29 Oct 2022 • Rakshith Subramanyam, Kowshik Thopalli, Spring Berman, Pavan Turaga, Jayaraman J. Thiagarajan
The problem of adapting models from a source domain using data from any target domain of interest has gained prominence, thanks to the brittle generalization in deep neural networks.
1 code implementation • 9 Jul 2022 • Kowshik Thopalli, Pavan Turaga, Jayaraman J. Thiagarajan
With a minimal overhead of storing the subspace basis set for the source data, CATTAn enables unsupervised alignment between source and target data during adaptation.
no code implementations • 24 May 2022 • Rajhans Singh, Ankita Shukla, Pavan Turaga
Deep networks for image classification often rely more on texture information than object shape.
1 code implementation • 1 Jan 2022 • Eun Som Jeon, Anirudh Som, Ankita Shukla, Kristina Hasanaj, Matthew P. Buman, Pavan Turaga
In this paper, we report the results of a detailed study that compares and contrasts various common choices and some hybrid data augmentation strategies in KD based human activity analysis.
1 code implementation • 17 Dec 2021 • Kowshik Thopalli, Sameeksha Katoch, Pavan Turaga, Jayaraman J. Thiagarajan
In this paper, we focus on the challenging problem of multi-source zero shot DG (MDG), where labeled training data from multiple source domains is available but with no access to data from the target domain.
Ranked #27 on
Domain Generalization
on TerraIncognita
1 code implementation • 28 Nov 2021 • John Kevin Cava, John Vant, Nicholas Ho, Ankita Shukla, Pavan Turaga, Ross Maciejewski, Abhishek Singharoy
In this paper, we utilized generative models, and reformulate it for problems in molecular dynamics (MD) simulation, by introducing an MD potential energy component to our generative model.
no code implementations • 24 Nov 2021 • Ankita Shukla, Rushil Anirudh, Eugene Kur, Jayaraman J. Thiagarajan, Peer-Timo Bremer, Brian K. Spears, Tammy Ma, Pavan Turaga
In this paper, we develop a Wasserstein autoencoder (WAE) with a hyperspherical prior for multimodal data in the application of inertial confinement fusion.
no code implementations • 2 Feb 2021 • Ella Y. Wang, Anirudh Som, Ankita Shukla, Hongjun Choi, Pavan Turaga
In addition to these findings, our work also presents a new application of the OS regularizer in healthcare, increasing the post-hoc interpretability and performance of deep learning models for COVID-19 classification to facilitate adoption of these methods in clinical settings.
no code implementations • 3 Dec 2020 • Suhas Lohit, Rushil Anirudh, Pavan Turaga
Motion capture (mocap) and time-of-flight based sensing of human actions are becoming increasingly popular modalities to perform robust activity analysis.
no code implementations • 22 Sep 2020 • Hongjun Choi, Anirudh Som, Pavan Turaga
Standard deep learning models that employ the categorical cross-entropy loss are known to perform well at image classification tasks.
1 code implementation • 18 Jun 2020 • Rushil Anirudh, Suhas Lohit, Pavan Turaga
In this paper, we propose the generative patch prior (GPP) that defines a generative prior for compressive image recovery, based on patch-manifold models.
no code implementations • 6 May 2020 • Anirudh Som, Narayanan Krishnamurthi, Matthew Buman, Pavan Turaga
We show that the features extracted for the target dataset can be used to train an effective classification model.
no code implementations • 6 May 2020 • Ankita Shukla, Pavan Turaga, Saket Anand
In this work, we propose a defense strategy that applies random image corruptions to the input image alone, constructs a self-correlation based subspace followed by a projection operation to suppress the adversarial perturbation.
1 code implementation • 21 Apr 2020 • Hongjun Choi, Anirudh Som, Pavan Turaga
We find that although the proposed geometrically constrained loss-function improves quantitative results modestly, it has a qualitatively surprisingly beneficial effect on increasing the interpretability of deep-net decisions as seen by the visual explanations generated by techniques such as the Grad-CAM.
no code implementations • 18 Apr 2020 • Kuldeep Kulkarni, Tejas Gokhale, Rajhans Singh, Pavan Turaga, Aswin Sankaranarayanan
The generated dense labelmap can then be used as input by state-of-the-art image synthesis techniques like pix2pixHD to obtain the final image.
1 code implementation • 15 Apr 2020 • Afra Nawar, Farhan Rahman, Narayanan Krishnamurthi, Anirudh Som, Pavan Turaga
In this paper, we propose to use Topological Data Analysis (TDA) together with machine learning tools to automate the process of Parkinson's disease classification and severity assessment.
no code implementations • 24 Nov 2019 • Sameeksha Katoch, Kowshik Thopalli, Jayaraman J. Thiagarajan, Pavan Turaga, Andreas Spanias
Exploiting known semantic relationships between fine-grained tasks is critical to the success of recent model agnostic approaches.
no code implementations • 22 Jul 2019 • Ankita Shukla, Sarthak Bhagat, Shagun Uppal, Saket Anand, Pavan Turaga
Learning representations that can disentangle explanatory attributes underlying the data improves interpretabilty as well as provides control on data generation.
1 code implementation • CVPR 2019 • Suhas Lohit, Qiao Wang, Pavan Turaga
We call this a temporal transformer network (TTN).
no code implementations • 11 Jun 2019 • Kowshik Thopalli, Jayaraman J. Thiagarajan, Rushil Anirudh, Pavan Turaga
This paper represents a hybrid approach, where we assume simplified data geometry in the form of subspaces, and consider alignment as an auxiliary task to the primary task of maximizing performance on the source.
1 code implementation • 5 Jun 2019 • Anirudh Som, Hongjun Choi, Karthikeyan Natesan Ramamurthy, Matthew Buman, Pavan Turaga
To the best of our knowledge, we are the first to propose the use of deep learning for computing topological features directly from data.
no code implementations • 16 May 2019 • Rajhans Singh, Pavan Turaga, Suren Jayasuriya, Ravi Garg, Martin W. Braun
The advent of generative adversarial networks (GAN) has enabled new capabilities in synthesis, interpolation, and data augmentation heretofore considered very challenging.
no code implementations • 19 Feb 2019 • Ankita Shukla, Shagun Uppal, Sarthak Bhagat, Saket Anand, Pavan Turaga
We use several metrics to compare the properties of latent spaces of disentangled representation models in terms of class separability and curvature of the latent-space.
1 code implementation • 20 Dec 2018 • Berkay Kanberoglu, Dhritiman Das, Priya Nair, Pavan Turaga, David Frakes
Three-dimensional (3D) biomedical image sets are often acquired with in-plane pixel spacings that are far less than the out-of-plane spacings between images.
no code implementations • 11 Nov 2018 • Kowshik Thopalli, Rushil Anirudh, Jayaraman J. Thiagarajan, Pavan Turaga
We present a novel unsupervised domain adaptation (DA) method for cross-domain visual recognition.
no code implementations • 8 Sep 2018 • Suhas Lohit, Rajhans Singh, Kuldeep Kulkarni, Pavan Turaga
Using standard datasets, we demonstrate that, when tested over a range of MRs, a rate-adaptive network can provide high quality reconstruction over a the entire range, resulting in up to about 15 dB improvement over previous methods, where the network is valid for only one MR. We demonstrate the effectiveness of our approach for sample-efficient object tracking where video frames are acquired at dynamically varying MRs. We also extend this algorithm to learn the measurement operator in conjunction with image recognition networks.
1 code implementation • ECCV 2018 • Anirudh Som, Kowshik Thopalli, Karthikeyan Natesan Ramamurthy, Vinay Venkataraman, Ankita Shukla, Pavan Turaga
However, persistence diagrams are multi-sets of points and hence it is not straightforward to fuse them with features used for contemporary machine learning tools like deep-nets.
no code implementations • 8 Jun 2018 • Li-Chi Huang, Kuldeep Kulkarni, Anik Jha, Suhas Lohit, Suren Jayasuriya, Pavan Turaga
Visual Question Answering (VQA) is a complex semantic task requiring both natural language processing and visual recognition.
no code implementations • 5 Feb 2018 • Mayank Gupta, Arjun Jauhari, Kuldeep Kulkarni, Suren Jayasuriya, Alyosha Molnar, Pavan Turaga
We test our network reconstructions on synthetic light fields, simulated coded measurements of real light fields captured from a Lytro Illum camera, and real coded images from a custom CMOS diffractive light field camera.
no code implementations • 30 Aug 2017 • Suhas Lohit, Pavan Turaga
Non-Euclidean constraints are inherent in many kinds of data in computer vision and machine learning, typically as a result of specific invariance requirements that need to be respected during high-level inference.
no code implementations • 15 Aug 2017 • Suhas Lohit, Kuldeep Kulkarni, Ronan Kerviche, Pavan Turaga, Amit Ashok
We show empirically that our algorithm yields reconstructions with higher PSNRs compared to iterative algorithms at low measurement rates and in presence of measurement noise.
no code implementations • 29 Oct 2016 • Rushil Anirudh, Ahnaf Masroor, Pavan Turaga
In this paper, we use diverse sampling for streaming video summarization.
no code implementations • CVPR 2016 • Kuldeep Kulkarni, Suhas Lohit, Pavan Turaga, Ronan Kerviche, Amit Ashok
The intermediate reconstruction is fed into an off-the-shelf denoiser to obtain the final reconstructed image.
1 code implementation • 28 May 2016 • Rushil Anirudh, Vinay Venkataraman, Karthikeyan Natesan Ramamurthy, Pavan Turaga
This paper concerns itself with one popular topological feature, which is the number of $d-$dimensional holes in the dataset, also known as the Betti$-d$ number.
no code implementations • 16 Mar 2016 • Vinay Venkataraman, Karthikeyan Natesan Ramamurthy, Pavan Turaga
In this paper, we propose a novel framework for dynamical analysis of human actions from 3D motion capture data using topological data analysis.
1 code implementation • 7 Mar 2016 • Rushil Anirudh, Pavan Turaga, Jingyong Su, Anuj Srivastava
We propose to learn an embedding such that each action trajectory is mapped to a single point in a low-dimensional Euclidean space, and the trajectories that differ only in temporal rates map to the same point.
no code implementations • 27 Jan 2016 • Vinay Venkataraman, Pavan Turaga
Our experimental analyses on these models also indicate that the proposed framework show stability for different time-series lengths, which is useful when the available number of samples are small/variable.
no code implementations • 27 Jan 2016 • Kuldeep Kulkarni, Pavan Turaga
We propose a framework called ReFInE to directly obtain integral image estimates from a very small number of spatially multiplexed measurements of the scene without iterative reconstruction of any auxiliary image, and demonstrate their practical utility in visual object tracking.
1 code implementation • CVPR 2016 • Kuldeep Kulkarni, Suhas Lohit, Pavan Turaga, Ronan Kerviche, Amit Ashok
The intermediate reconstruction is fed into an off-the-shelf denoiser to obtain the final reconstructed image.
no code implementations • CVPR 2015 • Rushil Anirudh, Pavan Turaga, Jingyong Su, Anuj Srivastava
Learning an accurate low dimensional embedding for actions could have a huge impact in the areas of efficient search and retrieval, visualization, learning, and recognition.
no code implementations • 18 Jan 2015 • Kuldeep Kulkarni, Pavan Turaga
In this paper, we propose reconstruction-free methods for action recognition from compressive cameras at high compression ratios of 100 and above.
no code implementations • 21 Jun 2014 • Rushil Anirudh, Pavan Turaga
To this end, we present the first system that estimates detector performance interactively without extensive ground truthing using a human in the loop.
no code implementations • 4 Mar 2014 • Rushil Anirudh, Pavan Turaga
This problem has several applications in the areas of human activity analysis, where there is a need to perform fast search, and recognition in very high dimensional spaces.
no code implementations • NeurIPS 2011 • Nitesh Shroff, Pavan Turaga, Rama Chellappa
In this paper, we consider the 'Precis' problem of sampling K representative yet diverse data points from a large dataset.