Search Results for author: Andreas Spanias

Found 24 papers, 3 papers with code

Adaptive Subsampling for ROI-based Visual Tracking: Algorithms and FPGA Implementation

no code implementations17 Dec 2021 Odrika Iqbal, Victor Isaac Torres Muro, Sameeksha Katoch, Andreas Spanias, Suren Jayasuriya

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.

Object Tracking Visual Tracking

Improving Multi-Domain Generalization through Domain Re-labeling

no code implementations17 Dec 2021 Kowshik Thopalli, Sameeksha Katoch, Andreas Spanias, Pavan Turaga, Jayaraman J. Thiagarajan

In this paper, we focus on the challenging problem of multi-source zero-shot DG, where labeled training data from multiple source domains is available but with no access to data from the target domain.

Domain Generalization

Designing Counterfactual Generators using Deep Model Inversion

no code implementations NeurIPS 2021 Jayaraman J. Thiagarajan, Vivek Narayanaswamy, Deepta Rajan, Jason Liang, Akshay Chaudhari, Andreas Spanias

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.

Image Generation

On the Design of Deep Priors for Unsupervised Audio Restoration

1 code implementation14 Apr 2021 Vivek Sivaraman Narayanaswamy, Jayaraman J. Thiagarajan, Andreas Spanias

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.

Audio Denoising Denoising

Loss Estimators Improve Model Generalization

no code implementations5 Mar 2021 Vivek Narayanaswamy, Jayaraman J. Thiagarajan, Deepta Rajan, Andreas Spanias

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

no code implementations22 Oct 2020 Vivek Narayanaswamy, Jayaraman J. Thiagarajan, Andreas Spanias

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.

Lesion Detection

Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks

no code implementations30 Sep 2020 Uday Shankar Shanthamallu, Jayaraman J. Thiagarajan, Andreas Spanias

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.

Graph Classification Link Prediction +1

Accurate and Robust Feature Importance Estimation under Distribution Shifts

no code implementations30 Sep 2020 Jayaraman J. Thiagarajan, Vivek Narayanaswamy, Rushil Anirudh, Peer-Timo Bremer, Andreas Spanias

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.

Feature Importance

Unsupervised Audio Source Separation using Generative Priors

1 code implementation28 May 2020 Vivek Narayanaswamy, Jayaraman J. Thiagarajan, Rushil Anirudh, Andreas Spanias

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.

Audio Source Separation

Audio Source Separation via Multi-Scale Learning with Dilated Dense U-Nets

no code implementations8 Apr 2019 Vivek Sivaraman Narayanaswamy, Sameeksha Katoch, Jayaraman J. Thiagarajan, Huan Song, Andreas Spanias

We also investigate the impact of dense connections on the extraction process that encourage feature reuse and better gradient flow.

Audio Source Separation

Designing an Effective Metric Learning Pipeline for Speaker Diarization

no code implementations1 Nov 2018 Vivek Sivaraman Narayanaswamy, Jayaraman J. Thiagarajan, Huan Song, Andreas Spanias

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.

Metric Learning Speaker Diarization

Attention Models with Random Features for Multi-layered Graph Embeddings

no code implementations2 Oct 2018 Uday Shankar Shanthamallu, Jayaraman J. Thiagarajan, Huan Song, Andreas Spanias

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.

Network Embedding Node Classification

Coverage-Based Designs Improve Sample Mining and Hyper-Parameter Optimization

1 code implementation5 Sep 2018 Gowtham Muniraju, Bhavya Kailkhura, Jayaraman J. Thiagarajan, Peer-Timo Bremer, Cihan Tepedelenlioglu, Andreas Spanias

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.

Data Summarization

Triplet Network with Attention for Speaker Diarization

no code implementations4 Aug 2018 Huan Song, Megan Willi, Jayaraman J. Thiagarajan, Visar Berisha, Andreas Spanias

In automatic speech processing systems, speaker diarization is a crucial front-end component to separate segments from different speakers.

Metric Learning Speaker Diarization

Optimizing Kernel Machines using Deep Learning

no code implementations15 Nov 2017 Huan Song, Jayaraman J. Thiagarajan, Prasanna Sattigeri, Andreas Spanias

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

no code implementations10 Nov 2017 Huan Song, Deepta Rajan, Jayaraman J. Thiagarajan, Andreas Spanias

With widespread adoption of electronic health records, there is an increased emphasis for predictive models that can effectively deal with clinical time-series data.

Time Series Time Series Analysis

Direct estimation of density functionals using a polynomial basis

no code implementations21 Feb 2017 Alan Wisler, Visar Berisha, Andreas Spanias, Alfred O. Hero

Typically, estimating these quantities requires complete knowledge of the underlying distribution followed by multi-dimensional integration.

Density Estimation

A Deep Learning Approach To Multiple Kernel Fusion

no code implementations28 Dec 2016 Huan Song, Jayaraman J. Thiagarajan, Prasanna Sattigeri, Karthikeyan Natesan Ramamurthy, Andreas Spanias

Kernel fusion is a popular and effective approach for combining multiple features that characterize different aspects of data.

Activity Recognition

Recovering Non-negative and Combined Sparse Representations

no code implementations12 Mar 2013 Karthikeyan Natesan Ramamurthy, Jayaraman J. Thiagarajan, Andreas Spanias

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

no code implementations3 Mar 2013 Jayaraman J. Thiagarajan, Karthikeyan Natesan Ramamurthy, Andreas Spanias

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.

Dictionary Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.