性能代价几何？面向细胞与细胞核实例分割的可持续性感知性能指标(SAPI)
Performance at What Cost? A Sustainability-Aware Performance Index for Cell and Nucleus Instance Segmentation
Eiram Mahera Sheikh · Alaa Tharwat · Wolfram Schenck
中文摘要
用于细胞与细胞核实例分割的预训练模型在架构、预训练数据与目标、参数量、推理策略、适配需求、后处理流程以及算力开销等方面差异显著。大型预训练模型与基础模型因其强大的零样本(zero-shot)能力而被广泛采用，但也带来了更高的能耗、显存占用、算力需求、适配代价以及运行阶段的碳排放。这些额外开销能否被分割性能上的实质提升所合理抵消，目前尚不明确。为回答这一问题，本文提出可持续性感知性能指标(SAPI)，一个可配置的复合指标，将分割性能、能耗与模型规模纳入统一衡量。在 6 个 CellBinDB 数据集上，对 19 个预训练模型与基础模型进行零样本推理评测；并对 16 个可微调模型分别采用冻结编码器与全模型微调两种少样本(few-shot)适配策略进行评估。GPU、CPU 与 RAM 的能耗通过软件监测工具估算。结果显示，模型规模更大、算力开销更高并不必然带来成比例的分割质量提升；少样本适配虽使部分模型受益，但收益与资源代价在不同架构、数据集与适配策略之间差异显著，导致基于 SAPI 的排名与仅基于性能的排名出现明显差异。本研究为分割模型的综合比较提供了实用框架，有助于在生物医学图像分析中以更易获取算力、更环境负责的方式进行模型选型。
关键要点
- 01提出可持续性感知性能指标 SAPI,综合分割性能、能耗与模型规模三个维度
- 02在 6 个 CellBinDB 数据集上评测 19 个零样本模型及 16 个少样本适配模型
- 03发现模型规模与算力开销的提升并不带来成比例的分割性能增益
- 04少样本适配对部分模型有效,但收益与代价因架构、数据集、适配策略而异
- 05SAPI 排名与纯性能排名差异显著,提示生物医学图像分析中需考虑可持续性
解读
尚无解读。
原始英文摘要
arXiv:2610.10324v1 Announce Type: new Abstract: Pretrained models for cell and nuclear instance segmentation differ substantially in architecture, pretraining data and objectives, parameter count, inference strategy, adaptation requirements, postprocessing pipeline, and computational demand. Large pretrained and foundation models are increasingly adopted because of their strong zero-shot capabilities, but their use also imposes greater energy consumption, memory requirements, computational demands, adaptation costs, and operational carbon emissions. Whether these additional demands are justified by meaningful gains in segmentation performance remains unclear. We address this question by introducing the Sustainability-Aware Performance Index (SAPI), a configurable metric that combines segmentation performance, energy consumption, and model size. We benchmark 19 pretrained and foundation models across six CellBinDB datasets under zero-shot inference and evaluate 16 fine-tunable models using few-shot adaptation with both frozen encoder and full-model fine-tuning. We estimate energy consumption for GPU, CPU, and RAM using software-based monitoring tools. Our results show that larger and more computationally demanding models do not consistently achieve proportionate improvements in segmentation quality. While few-shot adaptation benefits several models, the gains and resource costs vary considerably across architectures, datasets, and adaptation strategies, causing SAPI-based rankings to differ from rankings based on performance alone. This study provides a practical framework for comparing segmentation models more comprehensively and supports more computationally accessible and environmentally responsible model selection in biomedical image analysis.