面向单目视觉流的实时深度感知主动学习框架
An active-learning framework for real-time depth perception from monocular vision streams
- School of Mechanical and Automotive Engineering, Xiamen University of Technology（厦门理工学院机械与汽车工程学院）
- Xiamen Innovative Centre for Automotive Electric Driving（厦门新能源汽车驱动创新中心）
- King Long United Automotive Industry Co. Ltd.（金龙联合汽车工业有限公司）
- School of Electrical and Electronic Engineering, The University of Adelaide（阿德莱德大学电气与电子工程学院）
- School of Vehicle and Mobility, Tsinghua University（清华大学车辆与运载学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对边缘设备上单目深度感知的域偏移问题，提出带选择性可塑性的在线主动学习框架，以MobileNetV3-Small为骨干，在降75%计算量的同时实现高效深度估计。
AI中文摘要：
生物视觉系统可从单目视觉流中感知深度，在动态环境中持续整合时序视觉线索，同时维持稳定性与可塑性的平衡。相比之下，部署在资源受限边缘设备上的人工感知模型通常采用静态离线方式训练，部署后保持冻结状态，在域偏移场景下往往出现严重性能下降。尽管大规模模型可通过海量参数冗余编码广泛知识，但轻量级网络面临静态优化困境：迫使紧凑模型学习通用几何表征计算效率低下，且常导致性能饱和。为解决该问题，本文引入在线主动学习（Online Active Learning, OAL）机制，赋予紧凑神经网络在运行期间持续自适应的能力，构建闭环“预测-评估-修正”学习范式，从流式视觉输入中主动选择高置信度、高信息含量的信号。关键在于，本文采用弹性权重巩固（Elastic Weight Consolidation, EWC）不仅防止灾难性遗忘，还强制实现选择性可塑性，保留编码全局相关结构知识的参数，同时允许局部适配新观测环境。该系统以MobileNetV3-Small为骨干，在保持相当深度估计精度的同时，实现约75%的计算成本降低。实验结果表明，适应性并非仅由模型规模决定，而是取决于动态环境中参数可塑性的调控效果。
英文摘要：
Biological visual systems can perceive depth from monocular vision flow, continuously integrating temporal visual cues while maintaining a balance between stability and plasticity in dynamic environments. In contrast, artificial perception models deployed on resource-constrained edge devices are typically trained in a static offline manner and remain frozen after deployment, often suffering severe performance degradation under domain shifts. While large-scale models may encode broad knowledge through massive parameter redundancy, lightweight networks face a static optimization dilemma: forcing compact models to learn universal geometric representations is computationally inefficient and often leads to performance saturation. To resolve this issue, an Online Active Learning (OAL) mechanism is introduced to endow compact neural networks with the capability to adapt continuously during operation. A closed-loop Predict-Evaluate-Correct learning paradigm is established to actively select high-confidence, information-rich signals from streaming visual input. Crucially, Elastic Weight Consolidation (EWC) is employed not merely to prevent catastrophic forgetting, but to enforce Selective Plasticity, preserving parameters that encode globally relevant structural knowledge while allowing local alignment to newly observed environments. Built upon a MobileNetV3-Small backbone, the proposed system achieves approximately a 75% reduction in computational cost while maintaining competitive depth estimation accuracy. Experimental results demonstrate that adaptability is not solely determined by model size, but rather by how effectively parameter plasticity is regulated in dynamic environments.
