paper-with-me

홈 › Papers

Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimation

2023-03-09 · Junjie Hu, Chenyou Fan, Liguang Zhou, Qing Gao, Honghai Liu, Tin Lun Lam

With the rapid advancements in autonomous driving and robot navigation, there is a growing demand for lifelong learning models capable of estimating metric (absolute) depth. Lifelong learning approaches potentially offer significant cost savings in terms of model training, data storage, and collection. However, the quality of RGB images and depth maps is sensor-dependent, and depth maps in the real world exhibit domain-specific characteristics, leading to variations in depth ranges. These challenges limit existing methods to lifelong learning scenarios with small domain gaps and relative depth map estimation. To facilitate lifelong metric depth learning, we identify three crucial technical challenges that require attention: i) developing a model capable of addressing the depth scale variation through scale-aware depth learning, ii) devising an effective learning strategy to handle significant domain gaps, and iii) creating an automated solution for domain-aware depth inference in practical applications. Based on the aforementioned considerations, in this paper, we present i) a lightweight multi-head framework that effectively tackles the depth scale imbalance, ii) an uncertainty-aware lifelong learning solution that adeptly handles significant domain gaps, and iii) an online domain-specific predictor selection method for real-time inference. Through extensive numerical studies, we show that the proposed method can achieve good efficiency, stability, and plasticity, leading the benchmarks by 8% to 15%.

📄 PDF Abstract BibTeX arXiv:2303.05050

Code (1)

freeformrobotics/lifelong-monodepth 공식 구현 pytorch

Tasks

Autonomous DrivingDepth EstimationDepth PredictionLifelong learningMonocular Depth EstimationRobot Navigation

Similar Papers 제목 키워드 기반

Cross Domain LifeLong Sequential Modeling for Online Click-Through Rate Prediction

2023-12-11 · Ruijie Hou, Zhaoyang Yang, Yu Ming, Hongyu Lu 외

Deep neural networks (DNNs) that incorporated lifelong sequential modeling (LSM) have brought great success to recommendation systems in various social media platforms. While continuous improvements have been made in dom…

Click-Through Rate PredictionPredictionRecommendation Systems

Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning

2022-07-12 · Christian Steinparz, Thomas Schmied, Fabian Paischer, Marius-Constantin Dinu 외

In lifelong learning, an agent learns throughout its entire life without resets, in a constantly changing environment, as we humans do. Consequently, lifelong learning comes with a plethora of research problems such as c…

Lifelong learningPolicy Gradient MethodsQ-Learningreinforcement-learning+1

Lifelong Continual Learning for Anomaly Detection: New Challenges, Perspectives, and Insights

2023-03-14 · Kamil Faber, Roberto Corizzo, Bartlomiej Sniezynski, Nathalie Japkowicz

Anomaly detection is of paramount importance in many real-world domains, characterized by evolving behavior. Lifelong learning represents an emerging trend, answering the need for machine learning models that continuousl…

Anomaly DetectionContinual LearningLifelong learning

Lifelong Learning of Factored Policies via Policy Gradients

2020-06-12 · ICML Workshop LifelongML 2020 7 · Jorge A Mendez, Eric Eaton

Policy gradient methods have shown success in learning continuous control policies for high-dimensional dynamical systems. A major downside of such methods is the amount of exploration they require before yielding high-p…

continuous-controlContinuous ControlLifelong learningPolicy Gradient Methods

Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting

2020-07-14 · NeurIPS 2020 12 · Jorge A. Mendez, Boyu Wang, Eric Eaton

Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. I…

Lifelong learningPolicy Gradient Methods