June 10, 2024, 4:48 a.m. | Maying Shen, Hongxu Yin, Pavlo Molchanov, Lei Mao, Jose M. Alvarez

cs.CV updates on arXiv.org arxiv.org

arXiv:2406.04484v1 Announce Type: new
Abstract: Data often arrives in sequence over time in real-world deep learning applications such as autonomous driving. When new training data is available, training the model from scratch undermines the benefit of leveraging the learned knowledge, leading to significant training costs. Warm-starting from a previously trained checkpoint is the most intuitive way to retain knowledge and advance learning. However, existing literature suggests that this warm-starting degrades generalization. In this paper, we advocate for warm-starting but stepping …

abstract applications arxiv autonomous autonomous driving benefit costs cs.cv data deep learning driving incremental knowledge scratch seek training training costs training data type warm world

Senior Data Engineer

@ Displate | Warsaw

Professor/Associate Professor of Health Informatics [LKCMedicine]

@ Nanyang Technological University | NTU Novena Campus, Singapore

Research Fellow (Computer Science (and Engineering)/Electronic Engineering/Applied Mathematics/Perception Sciences)

@ Nanyang Technological University | NTU Main Campus, Singapore

Java Developer - Assistant Manager

@ State Street | Bengaluru, India

Senior Java/Python Developer

@ General Motors | Austin IT Innovation Center North - Austin IT Innovation Center North

Research Associate (Computer Engineering/Computer Science/Electronics Engineering)

@ Nanyang Technological University | NTU Main Campus, Singapore