Search Results for author:
Found 56 papers, 19 papers with code
Graph Network Modeling Techniques for Visualizing Human Mobility Patterns
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.
Automatic Temporal Segmentation for Post-Stroke Rehabilitation: A Keypoint Detection and Temporal Segmentation Approach for Small Datasets
Specifically, we perform temporal segmentation of video recordings to capture detailed activities during stroke patients' rehabilitation.
Role of Mixup in Topological Persistence Based Knowledge Distillation for Wearable Sensor Data
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.
Deep Geometric Moments Promote Shape Consistency in Text-to-3D Generation
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.
Topological Persistence Guided Knowledge Distillation for Wearable Sensor Data
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.
Leveraging Topological Guidance for Improved Knowledge Distillation
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.
Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks
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.
Target-Aware Generative Augmentations for Single-Shot Adaptation
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.
Learning Pose Image Manifolds Using Geometry-Preserving GANs and Elasticae
This paper investigates the challenge of learning image manifolds, specifically pose manifolds, of 3D objects using limited training data.
Polynomial Implicit Neural Representations For Large Diverse Datasets
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
Leveraging Angular Distributions for Improved Knowledge Distillation
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.
Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study
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.
Single-Shot Domain Adaptation via Target-Aware Generative Augmentation
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.
Domain Alignment Meets Fully Test-Time Adaptation
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.
Improving Shape Awareness and Interpretability in Deep Networks Using Geometric Moments
Deep networks for image classification often rely more on texture information than object shape.
Role of Data Augmentation Strategies in Knowledge Distillation for Wearable Sensor Data
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.
Automated Domain Discovery from Multiple Sources to Improve Zero-Shot Generalization
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
Towards Conditional Generation of Minimal Action Potential Pathways for Molecular Dynamics
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.
Geometric Priors for Scientific Generative Models in Inertial Confinement Fusion
In this paper, we develop a Wasserstein autoencoder (WAE) with a hyperspherical prior for multimodal data in the application of inertial confinement fusion.
Interpretable COVID-19 Chest X-Ray Classification via Orthogonality Constraint
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.
Recovering Trajectories of Unmarked Joints in 3D Human Actions Using Latent Space Optimization
Motion capture (mocap) and time-of-flight based sensing of human actions are becoming increasingly popular modalities to perform robust activity analysis.
Role of Orthogonality Constraints in Improving Properties of Deep Networks for Image Classification
Standard deep learning models that employ the categorical cross-entropy loss are known to perform well at image classification tasks.
Generative Patch Priors for Practical Compressive Image Recovery
In this paper, we propose the generative patch prior (GPP) that defines a generative prior for compressive image recovery, based on patch-manifold models.
Unsupervised Pre-trained Models from Healthy ADLs Improve Parkinson's Disease Classification of Gait Patterns
We show that the features extracted for the target dataset can be used to train an effective classification model.
GraCIAS: Grassmannian of Corrupted Images for Adversarial Security
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.
AMC-Loss: Angular Margin Contrastive Loss for Improved Explainability in Image Classification
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.
Halluci-Net: Scene Completion by Exploiting Object Co-occurrence Relationships
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.
Topological Descriptors for Parkinson's Disease Classification and Regression Analysis
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.
Invenio: Discovering Hidden Relationships Between Tasks/Domains Using Structured Meta Learning
Exploiting known semantic relationships between fine-grained tasks is critical to the success of recent model agnostic approaches.
Product of Orthogonal Spheres Parameterization for Disentangled Representation Learning
Learning representations that can disentangle explanatory attributes underlying the data improves interpretabilty as well as provides control on data generation.
Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping
We call this a temporal transformer network (TTN).
SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation
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.
PI-Net: A Deep Learning Approach to Extract Topological Persistence Images
To the best of our knowledge, we are the first to propose the use of deep learning for computing topological features directly from data.
Non-Parametric Priors For Generative Adversarial Networks
The advent of generative adversarial networks (GAN) has enabled new capabilities in synthesis, interpolation, and data augmentation heretofore considered very challenging.
Geometry of Deep Generative Models for Disentangled Representations
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.
An Optical Flow-Based Approach for Minimally-Divergent Velocimetry Data Interpolation
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.
Multiple Subspace Alignment Improves Domain Adaptation
We present a novel unsupervised domain adaptation (DA) method for cross-domain visual recognition.
Rate-Adaptive Neural Networks for Spatial Multiplexers
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.
Perturbation Robust Representations of Topological Persistence Diagrams
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.
CS-VQA: Visual Question Answering with Compressively Sensed Images
Visual Question Answering (VQA) is a complex semantic task requiring both natural language processing and visual recognition.
Compressive Light Field Reconstructions using Deep Learning
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.
Learning Invariant Riemannian Geometric Representations Using Deep Nets
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.
Convolutional Neural Networks for Non-iterative Reconstruction of Compressively Sensed Images
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.
Diversity Promoting Online Sampling for Streaming Video Summarization
In this paper, we use diverse sampling for streaming video summarization.
ReconNet: Non-Iterative Reconstruction of Images From Compressively Sensed Measurements
The intermediate reconstruction is fed into an off-the-shelf denoiser to obtain the final reconstructed image.
A Riemannian Framework for Statistical Analysis of Topological Persistence Diagrams
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.
Persistent Homology of Attractors For Action Recognition
In this paper, we propose a novel framework for dynamical analysis of human actions from 3D motion capture data using topological data analysis.
Elastic Functional Coding of Riemannian Trajectories
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.
Shape Distributions of Nonlinear Dynamical Systems for Video-based Inference
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.
Fast Integral Image Estimation at 1% measurement rate
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.
ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Random Measurements
The intermediate reconstruction is fed into an off-the-shelf denoiser to obtain the final reconstructed image.
Elastic Functional Coding of Human Actions: From Vector-Fields to Latent Variables
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.
Reconstruction-free action inference from compressive imagers
In this paper, we propose reconstruction-free methods for action recognition from compressive cameras at high compression ratios of 100 and above.
Interactively Test Driving an Object Detector: Estimating Performance on Unlabeled Data
To this end, we present the first system that estimates detector performance interactively without extensive ground truthing using a human in the loop.
Geometry-based Adaptive Symbolic Approximation for Fast Sequence Matching on Manifolds
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.
Manifold Precis: An Annealing Technique for Diverse Sampling of Manifolds
In this paper, we consider the 'Precis' problem of sampling K representative yet diverse data points from a large dataset.
