|国家预印本平台
首页|A Rigorous Behavior Assessment of CNNs Using a Data-Domain Sampling Regime

A Rigorous Behavior Assessment of CNNs Using a Data-Domain Sampling Regime

A Rigorous Behavior Assessment of CNNs Using a Data-Domain Sampling Regime

来源:Arxiv_logoArxiv
英文摘要

We present a data-domain sampling regime for quantifying CNNs' graphic perception behaviors. This regime lets us evaluate CNNs' ratio estimation ability in bar charts from three perspectives: sensitivity to training-test distribution discrepancies, stability to limited samples, and relative expertise to human observers. After analyzing 16 million trials from 800 CNNs models and 6,825 trials from 113 human participants, we arrived at a simple and actionable conclusion: CNNs can outperform humans and their biases simply depend on the training-test distance. We show evidence of this simple, elegant behavior of the machines when they interpret visualization images. osf.io/gfqc3 provides registration, the code for our sampling regime, and experimental results.

Shuning Jiang、Wei-Lun Chao、Daniel Haehn、Hanspeter Pfister、Jian Chen

计算技术、计算机技术

Shuning Jiang,Wei-Lun Chao,Daniel Haehn,Hanspeter Pfister,Jian Chen.A Rigorous Behavior Assessment of CNNs Using a Data-Domain Sampling Regime[EB/OL].(2025-07-05)[2025-07-16].https://arxiv.org/abs/2507.03866.点此复制

评论