用适配器高效迁移模型，让月球火星岩石分割更省带宽和内存。
Efficient Adaptation of Deep Neural Networks for Semantic Segmentation in Space Applications
- 在预训练模型中加入适配器，实现轻量级迁移学习。
- 层融合与适配器排序可使推理开销归零，降低传输成本。
- 适合资源受限的太空探测设备，推动边缘智能应用。
近年来，深度学习在计算机视觉任务中取得显著进展，为外星探索中的应用铺平了道路。由于新环境标注数据稀缺，迁移学习成为关键策略。本文首次评估了适配器在月球与火星地形岩石分割任务中用于高效迁移学习的可行性。研究发现，在预训练主干模型中合理嵌入适配器，可有效降低目标外星设备的带宽与内存需求。本文提出两种省存策略：层融合（将推理开销降至零）与适配器排序（进一步减少传输成本）。在嵌入式设备上评估了任务性能、内存占用与计算开销，揭示了多项权衡关系，为该领域后续研究提供了方向。
原文摘要 · Abstract (English)
In recent years, the application of Deep Learning techniques has shown remarkable success in various computer vision tasks, paving the way for their deployment in extraterrestrial exploration. Transfer learning has emerged as a powerful strategy for addressing the scarcity of labeled data in these novel environments. This paper represents one of the first efforts in evaluating the feasibility of employing adapters toward efficient transfer learning for rock segmentation in extraterrestrial landscapes, mainly focusing on lunar and martian terrains. Our work suggests that the use of adapters, strategically integrated into a pre-trained backbone model, can be successful in reducing both bandwidth and memory requirements for the target extraterrestrial device. In this study, we considered two memory-saving strategies: layer fusion (to reduce to zero the inference overhead) and an ``adapter ranking'' (to also reduce the transmission cost). Finally, we evaluate these results in terms of task performance, memory, and computation on embedded devices, evidencing trade-offs that open the road to more research in the field.
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。