提出GHOST方法，提升大模型对未知类的公平识别能力
GHOST: Gaussian Hypothesis Open-Set Technique
- 用类级高斯分布建模特征，免调超参数
- 通过Z-score归一化降低异常样本误判率
- 在多个数据集上显著超越现有方法
大规模识别方法的评估通常关注整体性能，但往往忽略各分类别表现差异，导致公平性问题和误代表。为解决开放集识别（OSR）中的公平性问题，我们发现类别间性能差异显著。提出无超参数的高斯假设开放集技术（GHOST），利用类级多元高斯分布与对角协方差矩阵建模深度特征。通过Z-score归一化对数几率，缓解特征幅值偏离模型预期带来的影响，从而降低网络对未知样本赋予高分的可能性。我们在多个ImageNet-1K预训练深度网络上评估GHOST，使用四个不同未知数据集测试，采用标准指标如AUOSCR、AUROC和FPR95，实现统计显著提升，推动大规模开放集识别的前沿进展。源码已公开。
原文摘要 · Abstract (English)
Evaluations of large-scale recognition methods typically focus on overall performance. While this approach is common, it often fails to provide insights into performance across individual classes, which can lead to fairness issues and misrepresentation. Addressing these gaps is crucial for accurately assessing how well methods handle novel or unseen classes and ensuring a fair evaluation. To address fairness in Open-Set Recognition (OSR), we demonstrate that per-class performance can vary dramatically. We introduce Gaussian Hypothesis Open Set Technique (GHOST), a novel hyperparameter-free algorithm that models deep features using class-wise multivariate Gaussian distributions with diagonal covariance matrices. We apply Z-score normalization to logits to mitigate the impact of feature magnitudes that deviate from the model's expectations, thereby reducing the likelihood of the network assigning a high score to an unknown sample. We evaluate GHOST across multiple ImageNet-1K pre-trained deep networks and test it with four different unknown datasets. Using standard metrics such as AUOSCR, AUROC and FPR95, we achieve statistically significant improvements, advancing the state-of-the-art in large-scale OSR. Source code is provided online.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。