共识与争议：刻画架构产生分歧的决策空间
Consensus vs. Controversy: Mapping the Decision Space Where Architectures Diverge
提供了一种按图像分歧程度划分分布尾部（高分歧 vs 低分歧）的分析框架，可用于指导模型选择与集成构建——在争议图像子集上挑选互补架构，比在整体精度上做集成更能带来收益。
原文依据 only the top 10% most controversial images drive the majority of architectural divergence
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论来自不同架构家族的现代计算机视觉模型，例如 CNN、视觉 Transformer 和 MLP-Mixer，在标准基准上取得了极为相似的总体性能，这掩盖了它们在处理视觉信息方式上可能存在的系统性差异。我们引入一个简单却富有揭示性的框架来定位预训练模型家族产生分歧之处：通过系统性地刻画图像分布中高分歧尾部与低分歧尾部。我们在 ImageNet 验证集上分析横跨三个架构家族的 12 个预训练模型，发现争议图像的分歧程度约为共识图像的 4.5 倍（争议分数：4.46）。尽管平均准确率约为 80%，模型仍表现出结构化的分歧模式：家族内一致性高于跨家族一致性，CNN 与 ViT 形成各自独立的聚类，而 MLP 的整体对齐度更低。关键在于，仅前 10% 最具争议的图像就驱动了大部分架构分歧，构成一个规模虽小但信息密集的子集，揭示了被总体指标所掩盖的根本差异。我们的分析表明，架构选择在这一集中的争议空间上影响最大，为研究者的模型选择与集成构建提供了可操作的指导。
英文原文摘要 1354 字符
Modern computer vision models from different architecture families, e.g., CNNs, Vision Transformers, and MLP-Mixers, achieve remarkably similar aggregate performance on standard benchmarks, masking potential systematic differences in how they process visual information. We introduce a simple yet revealing framework to identify where pretrained model families diverge: by systematically mapping the high-disagreement tail versus the low-disagreement tail of the image distribution. Analyzing 12 pretrained models spanning three architecture families on ImageNet validation set, we discover that controversial images exhibit approximately 4.5xhigher disagreement than consensus images (Controversy Score: 4.46). Despite mean accuracy around 80%, models show structured disagreement patterns: within-family agreement exceeds cross-family agreement, with CNNs and ViTs forming distinct clusters while MLPs show lower overall alignment. Crucially, only the top 10% most controversial images drive the majority of architectural divergence, constituting a small but informationally dense subset that reveals fundamental differences masked by aggregate metrics. Our analysis demonstrates that architectural choice matters most on this concentrated controversy space, providing researchers with actionable guidance for model selection and ensemble construction.