paper-with-me

홈 › Papers

Training Lightweight CNNs for Human-Nanodrone Proximity Interaction from Small Datasets using Background Randomization

2021-10-27 · Marco Ferri, Dario Mantegazza, Elia Cereda, Nicky Zimmerman, Luca M. Gambardella, Daniele Palossi, Jérôme Guzzi, Alessandro Giusti

We consider the task of visually estimating the pose of a human from images acquired by a nearby nano-drone; in this context, we propose a data augmentation approach based on synthetic background substitution to learn a lightweight CNN model from a small real-world training set. Experimental results on data from two different labs proves that the approach improves generalization to unseen environments.

📄 PDF Abstract BibTeX arXiv:2110.14491

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Similar Papers 제목 키워드 기반

Learning Long-Range Dependencies with Temporal Predictive Coding

2026-02-20 · Tom Potter, Oliver Rhodes arxiv

Temporal Predictive Coding provides a layer-local, parallelisable mechanism for learning in recurrent systems, making it an attractive candidate for online local learning on neuromorphic and edge hardware. However, its r…

Language Modelling

AuraSense: Robot Collision Avoidance by Full Surface Proximity Detection

2021-08-10 · Xiaoran Fan, Riley Simmons-Edler, Daewon Lee, Larry Jackel 외

Perceiving obstacles and avoiding collisions is fundamental to the safe operation of a robot system, particularly when the robot must operate in highly dynamic human environments. Proximity detection using on-robot senso…

Collision Avoidance

Layer-wise training convolutional neural networks with smaller filters for human activity recognition using wearable sensors

2020-05-08 · Yin Tang, Qi Teng, Lei Zhang, Fuhong Min 외

Recently, convolutional neural networks (CNNs) have set latest state-of-the-art on various human activity recognition (HAR) datasets. However, deep CNNs often require more computing resources, which limits their applicat…

Activity RecognitionHuman Activity RecognitionTime Series Analysis

Lightweight Transformer in Federated Setting for Human Activity Recognition

2021-10-01 · Ali Raza, Kim Phuc Tran, Ludovic Koehl, Shujun Li 외

Human activity recognition (HAR) is a machine learning task with important applications in healthcare especially in the context of home care of patients and older adults. HAR is often based on data collected from smart s…

Activity RecognitionFederated LearningHuman Activity Recognition

RepViT: Revisiting Mobile CNN From ViT Perspective

2023-07-18 · CVPR 2024 1 · Ao Wang, Hui Chen, Zijia Lin, Jungong Han 외

Recently, lightweight Vision Transformers (ViTs) demonstrate superior performance and lower latency, compared with lightweight Convolutional Neural Networks (CNNs), on resource-constrained mobile devices. Researchers hav…