← 研踪 PaperTrailarXiv:2611.13014 · v1
Is a CNN-Transformer Ensemble Worth It When a Chest X-Ray Foundation Model Is Available?
首次提交 2026-11-09 11:22
版本更新 2026-11-09 11:22
雷达观测 2026-11-11 11:05
摘要
Ensembles of ImageNet-pretrained convolutional networks and Vision Transformers are a common way to improve multi-label chest X-ray classification. We ask whether such an ensemble is still worth its cost when a model pretrained on chest radiographs is available. On the official patient-disjoint split of NIH ChestX-ray14 (25,596 test images, 2,797 patients), we train five ImageNet-pretrained backbones and the EVA-X-S foundation model with validation-only model selection, compare five fusion rules, and estimate every difference with a patient-level paired bootstrap. EVA-X-S alone reached a test macro-AUROC of 0.828; the five-model ensemble reached 0.814 (difference -0.0136, 95% CI -0.0178 to -0.0098) at about 7.8 times the summed backbone latency and ten times the parameters. Averaging the five ImageNet models with EVA-X-S changed AUROC by -0.0056 (-0.0095 to -0.0021). With all five ImageNet backbones trained with the EVA-X-S recipe, their ensemble scored 0.817, still -0.0109 (-0.0142 to -0.0076) below EVA-X-S, and across three seeds EVA-X-S varied by at most 0.001 AUROC. Under the ImageNet models' recipe, however, EVA-X-S fell to 0.798. Our full-stacking configuration never outperformed calibrated averaging. In this setting, the tested ImageNet ensembles did not improve on a single chest X-ray foundation model fine-tuned with its own recipe.
作者备注:8 pages, 2 figures, 10 tables. Code: https://github.com/adityaseelaboyina/cxr-ensemble-vs-foundation-model
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-09 11:22 · 最新观测版本
Is a CNN-Transformer Ensemble Worth It When a Chest X-Ray Foundation Model Is Available?
Ensembles of ImageNet-pretrained convolutional networks and Vision Transformers are a common way to improve multi-label chest X-ray classification. We ask whether such an ensemble is still worth its cost when a model pretrained on chest radiographs is available. On the official patient-disjoint split of NIH ChestX-ray14 (25,596 test images, 2,797 patients), we train five ImageNet-pretrained backbones and the EVA-X-S foundation model with validation-only model selection, compare five fusion rules, and estimate every difference with a patient-level paired bootstrap. EVA-X-S alone reached a test macro-AUROC of 0.828; the five-model ensemble reached 0.814 (difference -0.0136, 95% CI -0.0178 to -0.0098) at about 7.8 times the summed backbone latency and ten times the parameters. Averaging the five ImageNet models with EVA-X-S changed AUROC by -0.0056 (-0.0095 to -0.0021). With all five ImageNet backbones trained with the EVA-X-S recipe, their ensemble scored 0.817, still -0.0109 (-0.0142 to -0.0076) below EVA-X-S, and across three seeds EVA-X-S varied by at most 0.001 AUROC. Under the ImageNet models' recipe, however, EVA-X-S fell to 0.798. Our full-stacking configuration never outperformed calibrated averaging. In this setting, the tested ImageNet ensembles did not improve on a single chest X-ray foundation model fine-tuned with its own recipe.
查看此版本解读 →查看此版本原文 ↗