Performance at What Cost? A Sustainability-Aware Performance Index for Cell and Nucleus Instance Segmentation

Key points

• Whether these additional demands are justified by meaningful gains in segmentation performance remains unclear.1
• We address this question by introducing the Sustainability-Aware Performance Index (SAPI), a configurable metric that combines segmentation performance, energy consumption, and model size.1
• 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.1
• 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.1

Sources (1)

• [1]Performance at What Cost? A Sustainability-Aware Performance Index for Cell and Nucleus Instance Segmentation
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 04:12 PM

  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.

  Whether these additional demands are justified by meaningful gains in segmentation performance remains unclear.

Extractive summary: sentences quoted from the sources.