Search Results for author: Salimeh Yasaei Sekeh

Found 20 papers, 1 papers with code

Robust Subgraph Learning by Monitoring Early Training Representations

no code implementations14 Mar 2024 Sepideh Neshatfar, Salimeh Yasaei Sekeh

However, their vulnerability to adversarial attacks, particularly through susceptible nodes, poses a challenge in decision-making.

Adversarial Robustness Decision Making +2

FogGuard: guarding YOLO against fog using perceptual loss

1 code implementation13 Mar 2024 Soheil Gharatappeh, Sepideh Neshatfar, Salimeh Yasaei Sekeh, Vikas Dhiman

In this paper, we present a novel fog-aware object detection network called FogGuard, designed to address the challenges posed by foggy weather conditions.

Autonomous Driving Domain Adaptation +4

Towards Explaining Deep Neural Network Compression Through a Probabilistic Latent Space

no code implementations29 Feb 2024 Mahsa Mozafari-Nia, Salimeh Yasaei Sekeh

Despite the impressive performance of deep neural networks (DNNs), their computational complexity and storage space consumption have led to the concept of network compression.

Neural Network Compression

A Theoretical Perspective on Subnetwork Contributions to Adversarial Robustness

no code implementations7 Jul 2023 Jovon Craig, Josh Andle, Theodore S. Nowak, Salimeh Yasaei Sekeh

To better understand these attacks and facilitate more efficient adversarial training, in this paper we develop a novel theoretical framework that investigates how the adversarial robustness of a subnetwork contributes to the robustness of the entire network.

Adversarial Robustness

Promise and Limitations of Supervised Optimal Transport-Based Graph Summarization via Information Theoretic Measures

no code implementations11 May 2023 Sepideh Neshatfar, Abram Magner, Salimeh Yasaei Sekeh

To gain a theoretical perspective on the supervised summarization problem itself, we first formulate it in terms of maximizing the Shannon mutual information between the summarized graph and the class label.

Attribute

Improving Hyperspectral Adversarial Robustness Under Multiple Attacks

no code implementations28 Oct 2022 Nicholas Soucy, Salimeh Yasaei Sekeh

Semantic segmentation models classifying hyperspectral images (HSI) are vulnerable to adversarial examples.

Adversarial Robustness Semantic Segmentation +1

Theoretical Understanding of the Information Flow on Continual Learning Performance

no code implementations26 Apr 2022 Josh Andle, Salimeh Yasaei Sekeh

Despite the numerous previous solutions to bypass the catastrophic forgetting (CF) of previously seen tasks during the learning process, most of them still suffer significant forgetting, expensive memory cost, or lack of theoretical understanding of neural networks' conduct while learning new tasks.

Continual Learning

Q-TART: Quickly Training for Adversarial Robustness and in-Transferability

no code implementations14 Apr 2022 Madan Ravi Ganesh, Salimeh Yasaei Sekeh, Jason J. Corso

Raw deep neural network (DNN) performance is not enough; in real-world settings, computational load, training efficiency and adversarial security are just as or even more important.

Adversarial Robustness

The Stanford Drone Dataset is More Complex than We Think: An Analysis of Key Characteristics

no code implementations22 Mar 2022 Joshua Andle, Nicholas Soucy, Simon Socolow, Salimeh Yasaei Sekeh

Our contributions include the outlining of key characteristics in the SDD, employment of an information-theoretic measure and custom metric to clearly visualize those characteristics, the implementation of the PECNet and Y-Net trajectory prediction models to demonstrate the outlined characteristics' impact on predictive performance, and lastly we provide a comparison between the SDD and Intersection Drone (inD) Dataset.

Autonomous Navigation Trajectory Prediction

CEU-Net: Ensemble Semantic Segmentation of Hyperspectral Images Using Clustering

no code implementations9 Mar 2022 Nicholas Soucy, Salimeh Yasaei Sekeh

These approaches use patching to incorporate the rich neighborhood information in images and exploit the simplicity and segmentability of the most common HSI datasets.

Clustering Clustering Ensemble +2

Slimming Neural Networks using Adaptive Connectivity Scores

no code implementations22 Jun 2020 Madan Ravi Ganesh, Dawsin Blanchard, Jason J. Corso, Salimeh Yasaei Sekeh

Finally, we define a novel sensitivity criterion for filters that measures the strength of their contributions to the succeeding layer and highlights critical filters that need to be completely protected from pruning.

MINT: Deep Network Compression via Mutual Information-based Neuron Trimming

no code implementations18 Mar 2020 Madan Ravi Ganesh, Jason J. Corso, Salimeh Yasaei Sekeh

Most approaches to deep neural network compression via pruning either evaluate a filter's importance using its weights or optimize an alternative objective function with sparsity constraints.

Neural Network Compression

A Geometric Approach to Online Streaming Feature Selection

no code implementations2 Oct 2019 Salimeh Yasaei Sekeh, Madan Ravi Ganesh, Shurjo Banerjee, Jason J. Corso, Alfred O. Hero

In this work, firstly, we assert that OSFS's main assumption of having data from all the samples available at runtime is unrealistic and introduce a new setting where features and samples are streamed concurrently called OSFS with Streaming Samples (OSFS-SS).

feature selection

Geometric Estimation of Multivariate Dependency

no code implementations21 May 2019 Salimeh Yasaei Sekeh, Alfred O. Hero

This paper proposes a geometric estimator of dependency between a pair of multivariate samples.

Density Estimation

Learning to Bound the Multi-class Bayes Error

no code implementations15 Nov 2018 Salimeh Yasaei Sekeh, Brandon Oselio, Alfred O. Hero

Providing a tight bound on the BER that is also feasible to estimate has been a challenge.

Meta-Learning

Convergence Rates for Empirical Estimation of Binary Classification Bounds

no code implementations1 Oct 2018 Salimeh Yasaei Sekeh, Morteza Noshad, Kevin R. Moon, Alfred O. Hero

We derive a bound on the convergence rate for the Friedman-Rafsky (FR) estimator of the HP-divergence, which is related to a multivariate runs statistic for testing between two distributions.

Binary Classification Classification +1

Direct Estimation of Information Divergence Using Nearest Neighbor Ratios

no code implementations17 Feb 2017 Morteza Noshad, Kevin R. Moon, Salimeh Yasaei Sekeh, Alfred O. Hero III

Considering the $k$-nearest neighbor ($k$-NN) graph of $Y$ in the joint data set $(X, Y)$, we show that the average powered ratio of the number of $X$ points to the number of $Y$ points among all $k$-NN points is proportional to R\'{e}nyi divergence of $X$ and $Y$ densities.

Information Theoretic Structure Learning with Confidence

no code implementations13 Sep 2016 Kevin R. Moon, Morteza Noshad, Salimeh Yasaei Sekeh, Alfred O. Hero III

Information theoretic measures (e. g. the Kullback Liebler divergence and Shannon mutual information) have been used for exploring possibly nonlinear multivariate dependencies in high dimension.

Two-sample testing

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