FrameHopper: Selective Processing of Video Frames in Detection-driven Real-Time Video Analytics

no code implementations • 22 Mar 2022 • Md Adnan Arefeen, Sumaiya Tabassum Nimi, Md Yusuf Sarwar Uddin

Detection-driven real-time video analytics require continuous detection of objects contained in the video frames using deep learning models like YOLOV3, EfficientDet.

object-detection Object Detection +1

EARLIN: Early Out-of-Distribution Detection for Resource-efficient Collaborative Inference

no code implementations • 25 Jun 2021 • Sumaiya Tabassum Nimi, Md Adnan Arefeen, Md Yusuf Sarwar Uddin, Yugyung Lee

Collaborative inference enables resource-constrained edge devices to make inferences by uploading inputs (e. g., images) to a server (i. e., cloud) where the heavy deep learning models run.

Collaborative Inference Out-of-Distribution Detection +1

A Lightweight ReLU-Based Feature Fusion for Aerial Scene Classification

no code implementations • 15 Jun 2021 • Md Adnan Arefeen, Sumaiya Tabassum Nimi, Md Yusuf Sarwar Uddin, Zhu Li

In this paper, we propose a transfer-learning based model construction technique for the aerial scene classification problem.

Aerial Scene Classification Classification +4

Neural Network Based Undersampling Techniques

no code implementations • 18 Aug 2019 • Md. Adnan Arefeen, Sumaiya Tabassum Nimi, M. Sohel Rahman

Several researches have been done to tackle this problem, most of which employed resampling, i. e. oversampling and undersampling techniques to bring the required balance in the data.