Search Results for author:
Found 27 papers, 4 papers with code
Infrared Computer Vision for Utility-Scale Photovoltaic Array Inspection
We demonstrate our infrared thermography data collection approach, the PV thermal imagery benchmark dataset, and the measured performance of image processing transformations, including the Hough Transform for PV segmentation.
An L2-Normalized Spatial Attention Network For Accurate And Fast Classification Of Brain Tumors In 2D T1-Weighted CE-MRI Images
We compare our results against the state-of-the-art on this dataset and show that by integrating l2-normalized spatial attention into a baseline network we achieve a performance gain of 1. 79 percentage points.
Towards Live 3D Reconstruction from Wearable Video: An Evaluation of V-SLAM, NeRF, and Videogrammetry Techniques
3D reconstruction algorithms should utilize the low cost and pervasiveness of video camera sensors, from both overhead and soldier-level perspectives.
Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors
We focus on the problem of producing well-calibrated out-of-distribution (OOD) detectors, in order to enable safe deployment of medical image classifiers.
Adaptive Subsampling for ROI-based Visual Tracking: Algorithms and FPGA Implementation
Our adaptive subsampling algorithms comprise an object detector and an ROI predictor (Kalman filter) which operate in conjunction to optimize the energy efficiency of the vision pipeline with the end task being object tracking.
Designing Counterfactual Generators using Deep Model Inversion
Explanation techniques that synthesize small, interpretable changes to a given image while producing desired changes in the model prediction have become popular for introspecting black-box models.
On the Design of Deep Priors for Unsupervised Audio Restoration
Unsupervised deep learning methods for solving audio restoration problems extensively rely on carefully tailored neural architectures that carry strong inductive biases for defining priors in the time or spectral domain.
Loss Estimators Improve Model Generalization
With increased interest in adopting AI methods for clinical diagnosis, a vital step towards safe deployment of such tools is to ensure that the models not only produce accurate predictions but also do not generalize to data regimes where the training data provide no meaningful evidence.
Using Deep Image Priors to Generate Counterfactual Explanations
Through the use of carefully tailored convolutional neural network architectures, a deep image prior (DIP) can be used to obtain pre-images from latent representation encodings.
Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks
In this work, we propose Uncertainty Matching GNN (UM-GNN), that is aimed at improving the robustness of GNN models, particularly against poisoning attacks to the graph structure, by leveraging epistemic uncertainties from the message passing framework.
Accurate and Robust Feature Importance Estimation under Distribution Shifts
With increasing reliance on the outcomes of black-box models in critical applications, post-hoc explainability tools that do not require access to the model internals are often used to enable humans understand and trust these models.
Unsupervised Audio Source Separation using Generative Priors
State-of-the-art under-determined audio source separation systems rely on supervised end-end training of carefully tailored neural network architectures operating either in the time or the spectral domain.
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.
Audio Source Separation via Multi-Scale Learning with Dilated Dense U-Nets
We also investigate the impact of dense connections on the extraction process that encourage feature reuse and better gradient flow.
Designing an Effective Metric Learning Pipeline for Speaker Diarization
State-of-the-art speaker diarization systems utilize knowledge from external data, in the form of a pre-trained distance metric, to effectively determine relative speaker identities to unseen data.
A Regularized Attention Mechanism for Graph Attention Networks
Machine learning models that can exploit the inherent structure in data have gained prominence.
Attention Models with Random Features for Multi-layered Graph Embeddings
Though deep network embeddings, e. g. DeepWalk, are widely adopted for community discovery, we argue that feature learning with random node attributes, using graph neural networks, can be more effective.
Coverage-Based Designs Improve Sample Mining and Hyper-Parameter Optimization
Sampling one or more effective solutions from large search spaces is a recurring idea in machine learning, and sequential optimization has become a popular solution.
Triplet Network with Attention for Speaker Diarization
In automatic speech processing systems, speaker diarization is a crucial front-end component to separate segments from different speakers.
Optimizing Kernel Machines using Deep Learning
To this end, we develop the DKMO (Deep Kernel Machine Optimization) framework, that creates an ensemble of dense embeddings using Nystrom kernel approximations and utilizes deep learning to generate task-specific representations through the fusion of the embeddings.
Attend and Diagnose: Clinical Time Series Analysis using Attention Models
With widespread adoption of electronic health records, there is an increased emphasis for predictive models that can effectively deal with clinical time-series data.
Direct estimation of density functionals using a polynomial basis
Typically, estimating these quantities requires complete knowledge of the underlying distribution followed by multi-dimensional integration.
A Deep Learning Approach To Multiple Kernel Fusion
Kernel fusion is a popular and effective approach for combining multiple features that characterize different aspects of data.
Empirically Estimable Classification Bounds Based on a New Divergence Measure
Information divergence functions play a critical role in statistics and information theory.
Recovering Non-negative and Combined Sparse Representations
For case (c), we propose the combined orthogonal matching pursuit algorithm for coefficient recovery and derive the deterministic sparsity threshold under which recovery of the unique, sparsest coefficient vector is possible.
Learning Stable Multilevel Dictionaries for Sparse Representations
Algorithmic stability and generalization are desirable characteristics for dictionary learning algorithms that aim to build global dictionaries which can efficiently model any test data similar to the training samples.
Multiple Kernel Sparse Representations for Supervised and Unsupervised Learning
Descriptors that have diverse forms can be fused into a unified feature space in a principled manner using kernel methods.
