Search Results for author: Senem Velipasalar

Found 38 papers, 12 papers with code

Feature-based Federated Transfer Learning: Communication Efficiency, Robustness and Privacy

1 code implementation15 May 2024 Feng Wang, M. Cenk Gursoy, Senem Velipasalar

In this paper, we propose feature-based federated transfer learning as a novel approach to improve communication efficiency by reducing the uplink payload by multiple orders of magnitude compared to that of existing approaches in federated learning and federated transfer learning.

Federated Learning Image Classification +2

Block-As-Domain Adaptation for Workload Prediction from fNIRS Data

no code implementations30 Apr 2024 Jiyang Wang, Ayse Altay, Senem Velipasalar

To address these issues, we propose an effective method, referred to as the class-aware-block-aware domain adaptation (CABA-DA) which explicitly minimize intra-session variance by viewing different blocks from the same subject same session as different domains.

Contrastive Learning Domain Adaptation

GaitPoint+: A Gait Recognition Network Incorporating Point Cloud Analysis and Recycling

no code implementations16 Apr 2024 Huantao Ren, Jiajing Chen, Senem Velipasalar

Our approach models skeleton key points as a 3D point cloud, and employs a computational complexity-conscious 3D point processing approach to extract skeleton features, which are then combined with silhouette features for improved accuracy.

Gait Recognition Pose Estimation

Only My Model On My Data: A Privacy Preserving Approach Protecting one Model and Deceiving Unauthorized Black-Box Models

no code implementations14 Feb 2024 Weiheng Chai, Brian Testa, Huantao Ren, Asif Salekin, Senem Velipasalar

The datasets employed are ImageNet, for image classification, Celeba-HQ dataset, for identity classification, and AffectNet, for emotion classification.

Adversarial Attack Emotion Classification +4

Anomaly Detection via Learning-Based Sequential Controlled Sensing

no code implementations30 Nov 2023 Geethu Joseph, Chen Zhong, M. Cenk Gursoy, Senem Velipasalar, Pramod K. Varshney

Our objective is to design a sequential selection policy that dynamically determines which processes to observe at each time with the goal to minimize the delay in making the decision and the total sensing cost.

Anomaly Detection Decision Making +1

Robust Network Slicing: Multi-Agent Policies, Adversarial Attacks, and Defensive Strategies

no code implementations19 Nov 2023 Feng Wang, M. Cenk Gursoy, Senem Velipasalar

We evaluate the performance of the proposed policy ensemble algorithm by applying on the network slicing agents and the jammer agent in simulations to show its effectiveness.

Maximum Knowledge Orthogonality Reconstruction with Gradients in Federated Learning

1 code implementation30 Oct 2023 Feng Wang, Senem Velipasalar, M. Cenk Gursoy

MKOR only requires the server to send secretly modified parameters to clients and can efficiently and inconspicuously reconstruct the input images from clients' gradient updates.

Federated Learning

Vision-Language Models can Identify Distracted Driver Behavior from Naturalistic Videos

1 code implementation16 Jun 2023 Md Zahid Hasan, Jiajing Chen, Jiyang Wang, Mohammed Shaiqur Rahman, Ameya Joshi, Senem Velipasalar, Chinmay Hegde, Anuj Sharma, Soumik Sarkar

Our results show that this framework offers state-of-the-art performance on zero-shot transfer and video-based CLIP for predicting the driver's state on two public datasets.

Activity Recognition

SVT: Supertoken Video Transformer for Efficient Video Understanding

no code implementations1 Apr 2023 Chenbin Pan, Rui Hou, Hanchao Yu, Qifan Wang, Senem Velipasalar, Madian Khabsa

Whether by processing videos with fixed resolution from start to end or incorporating pooling and down-scaling strategies, existing video transformers process the whole video content throughout the network without specially handling the large portions of redundant information.

Video Understanding

EgoViT: Pyramid Video Transformer for Egocentric Action Recognition

no code implementations15 Mar 2023 Chenbin Pan, Zhiqi Zhang, Senem Velipasalar, Yi Xu

Different from previous video transformers, which use the same static embedding as the class token for diverse inputs, we propose a dynamic class token generator that produces a class token for each input video by analyzing the hand-object interaction and the related motion information.

Action Recognition

Communication-Efficient and Privacy-Preserving Feature-based Federated Transfer Learning

1 code implementation12 Sep 2022 Feng Wang, M. Cenk Gursoy, Senem Velipasalar

In order to improve the communication efficiency, we in this paper propose the feature-based federated transfer learning as an innovative approach to reduce the uplink payload by more than five orders of magnitude compared to that of existing approaches.

Federated Learning Image Classification +2

Why Discard if You Can Recycle?: A Recycling Max Pooling Module for 3D Point Cloud Analysis

1 code implementation CVPR 2022 Jiajing Chen, Burak Kakillioglu, Huantao Ren, Senem Velipasalar

In order to address this issue and improve the performance of any baseline 3D point classification or segmentation model, we propose a new module, referred to as the Recycling MaxPooling (RMP) module, to recycle and utilize the features of some of the discarded points.

Point Cloud Classification Semantic Segmentation

Scalable and Decentralized Algorithms for Anomaly Detection via Learning-Based Controlled Sensing

no code implementations8 Dec 2021 Geethu Joseph, Chen Zhong, M. Cenk Gursoy, Senem Velipasalar, Pramod K. Varshney

In this setting, we develop an anomaly detection algorithm that chooses the processes to be observed at a given time instant, decides when to stop taking observations, and declares the decision on anomalous processes.

Anomaly Detection Decision Making

Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Point Density Level Estimation

1 code implementation18 Nov 2021 Yantao Lu, Xuetao Hao, Yilan Li, Weiheng Chai, Shiqi Sun, Senem Velipasalar

It is worth to note that our proposed RAA convolution is lightweight and compatible to be integrated into any CNN architecture used for detection from a BEV.

3D Object Detection Autonomous Driving +2

Background-Aware 3D Point Cloud Segmentationwith Dynamic Point Feature Aggregation

no code implementations14 Nov 2021 Jiajing Chen, Burak Kakillioglu, Senem Velipasalar

As the core module of the DPFA-Net, we propose a Feature Aggregation layer, in which features of the dynamic neighborhood of each point are aggregated via a self-attention mechanism.

3D Object Classification Point Cloud Segmentation +2

Anomaly Detection via Controlled Sensing and Deep Active Inference

no code implementations12 May 2021 Geethu Joseph, Chen Zhong, M. Cenk Gursoy, Senem Velipasalar, Pramod K. Varshney

In this paper, we address the anomaly detection problem where the objective is to find the anomalous processes among a given set of processes.

Anomaly Detection Decision Making

Adversarial Reinforcement Learning in Dynamic Channel Access and Power Control

no code implementations12 May 2021 Feng Wang, M. Cenk Gursoy, Senem Velipasalar

Deep reinforcement learning (DRL) has recently been used to perform efficient resource allocation in wireless communications.

reinforcement-learning Reinforcement Learning (RL)

PT-CapsNet: A Novel Prediction-Tuning Capsule Network Suitable for Deeper Architectures

1 code implementation ICCV 2021 Chenbin Pan, Senem Velipasalar

Existing variations of CapsNets mainly focus on performance comparison with the original CapsNet, and have not outperformed CNN-based models on complex tasks.

object-detection Object Detection +1

Anomaly Detection and Sampling Cost Control via Hierarchical GANs

no code implementations28 Sep 2020 Chen Zhong, M. Cenk Gursoy, Senem Velipasalar

In order to improve the detection accuracy and reduce the delay in detection, we introduce a buffer zone in the operation of the proposed GAN-based detector.

Anomaly Detection Time Series Analysis

Adversarial jamming attacks and defense strategies via adaptive deep reinforcement learning

no code implementations12 Jul 2020 Feng Wang, Chen Zhong, M. Cenk Gursoy, Senem Velipasalar

As the applications of deep reinforcement learning (DRL) in wireless communications grow, sensitivity of DRL based wireless communication strategies against adversarial attacks has started to draw increasing attention.

Decision Making reinforcement-learning +1

Weighted Average Precision: Adversarial Example Detection in the Visual Perception of Autonomous Vehicles

1 code implementation25 Jan 2020 Yilan Li, Senem Velipasalar

Several research work in adversarial machine learning started to focus on the detection of AEs in autonomous driving.

Autonomous Driving object-detection +1

Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction

2 code implementations CVPR 2020 Yantao Lu, Yunhan Jia, Jian-Yu Wang, Bai Li, Weiheng Chai, Lawrence Carin, Senem Velipasalar

Neural networks are known to be vulnerable to carefully crafted adversarial examples, and these malicious samples often transfer, i. e., they remain adversarial even against other models.

Adversarial Attack Image Classification +5

Deep Actor-Critic Reinforcement Learning for Anomaly Detection

no code implementations28 Aug 2019 Chen Zhong, M. Cenk Gursoy, Senem Velipasalar

Anomaly detection is widely applied in a variety of domains, involving for instance, smart home systems, network traffic monitoring, IoT applications and sensor networks.

Anomaly Detection reinforcement-learning +1

Autonomous Human Activity Classification from Ego-vision Camera and Accelerometer Data

no code implementations28 May 2019 Yantao Lu, Senem Velipasalar

For instance, the sitting activity can be detected by IMU data, but it cannot be determined whether the subject has sat on a chair or a sofa, or where the subject is.

General Classification Multimodal Activity Recognition

Enhancing Cross-task Transferability of Adversarial Examples with Dispersion Reduction

1 code implementation8 May 2019 Yunhan Jia, Yantao Lu, Senem Velipasalar, Zhenyu Zhong, Tao Wei

Neural networks are known to be vulnerable to carefully crafted adversarial examples, and these malicious samples often transfer, i. e., they maintain their effectiveness even against other models.

Image Classification object-detection +3

Power Control for Wireless VBR Video Streaming: From Optimization to Reinforcement Learning

no code implementations31 Mar 2019 Chuang Ye, M. Cenk Gursoy, Senem Velipasalar

Dynamic programming is employed to implement the optimal offline and the initial online power control policies that minimize the transmit power consumption in the communication session.

reinforcement-learning Reinforcement Learning (RL)

Deep Learning Based Power Control for Quality-Driven Wireless Video Transmissions

no code implementations16 Oct 2018 Chuang Ye, M. Cenk Gursoy, Senem Velipasalar

In this paper, wireless video transmission to multiple users under total transmission power and minimum required video quality constraints is studied.

Actor-Critic Deep Reinforcement Learning for Dynamic Multichannel Access

no code implementations8 Oct 2018 Chen Zhong, Ziyang Lu, M. Cenk Gursoy, Senem Velipasalar

We consider the dynamic multichannel access problem, which can be formulated as a partially observable Markov decision process (POMDP).

reinforcement-learning Reinforcement Learning (RL)

Autonomously and Simultaneously Refining Deep Neural Network Parameters by a Bi-Generative Adversarial Network Aided Genetic Algorithm

no code implementations24 Sep 2018 Yantao Lu, Burak Kakillioglu, Senem Velipasalar

The choice of parameters, and the design of the network architecture are important factors affecting the performance of deep neural networks.

Generative Adversarial Network

Autonomously and Simultaneously Refining Deep Neural Network Parameters by Generative Adversarial Networks

no code implementations24 May 2018 Burak Kakillioglu, Yantao Lu, Senem Velipasalar

Our proposed approach can be used to autonomously refine the parameters, and improve the accuracy of different deep neural network architectures.

Generative Adversarial Network

Accelerometer based Activity Classification with Variational Inference on Sticky HDP-SLDS

no code implementations19 Oct 2015 Mehmet Emin Basbug, Koray Ozcan, Senem Velipasalar

With the advent of smartphones equipped with acceloremeter, gyroscope and camera; it is now possible to develop activity classification platforms everyone can use conveniently.

General Classification Time Series +2

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