轻量级网络提升机器人感知能力，兼顾精度与实时性
Lightweight Neural Networks for Affordance Segmentation: Enhancement of the Decoder Module
- 改进解码器模块，平衡分割精度与计算开销
- 在真实数据集上超越现有基线模型，且推理低耗
- 适合资源受限的可穿戴机器人部署
将深度神经网络用于可穿戴机器人视觉通路分割面临严峻挑战，因任务本身存在矛盾：一方面需高层抽象能力，通常依赖大模型；另一方面可穿戴设备算力有限，难以支持大模型实时运行。本文分析了分割头在泛化性能与计算成本之间的权衡作用，提出优化后的轻量级解码器结构。所提模型在多个真实世界公开数据集上表现优于当前主流基线方法，同时满足低计算需求，具备实际部署可行性。
原文摘要 · Abstract (English)
The deployment of deep neural networks for visual affordance segmentation on wearable robots poses may prove critical, due to some conflicting aspects of the problem. On one hand, affordance segmentation requires high-level abstraction capabilities, that typically involve large-size models. On the other hand, computing resources hosted on wearable robots prevent to run large-size models in real-time. The paper presents an analysis of the role of the segmentation head in the trade-off between generalization performance and compute cost. The obtained models outperform modern baseline solutions in well-known, real-world datasets while meeting low computing requirements.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。