提出新方法识别高置信度近似未知样本，提升开放集识别可靠性。
Evidence-Guided Unknown Rejection for High-Confidence Near-Known Unknowns
- 从‘得分是否够高’转为‘已知类别是否有充分证据接受该样本’
- 在多个数据集上显著降低高置信度误判率，且无需未知数据验证
- 适合需要高可信度分类的工业场景，如医疗、自动驾驶
开放集识别系统存在一个被忽视的失效模式：高置信度近似未知样本，即虽不属于已知类别但与已知类过于接近，导致闭集分类器以高置信度错误接受。我们发现此问题广泛存在于标量阈值方法中，包括近期后处理检测器，且更强编码器反而加剧风险。本文提出EGUR-A，将决策逻辑从‘样本得分是否足够高’转变为‘预测的已知类别是否有足够证据接受该样本’。EGUR-A结合类条件局部接受证据与全局残差证据，并通过已知样本统计量自动选择权重，无需未知数据验证。在CUB、FGVC-Aircraft和ImageNet-hard上，EGUR-A在相同已知拒绝率下显著降低高置信度误接受率。核心并非更强阈值，而是改变判断标准：已知类别是否有资格接纳该样本。
原文摘要 · Abstract (English)
Open-set recognition systems face a neglected failure mode: high-confidence near-known unknowns, which lie outside the known label set but are close enough to known classes that a closed-set classifier accepts them with high confidence. We show that this failure is widespread across scalar-threshold methods, including recent post-hoc detectors, and that stronger encoders can amplify rather than remove the risk. We propose EGUR-A, which changes the decision from ``is this sample's score high enough?'' to ``does this predicted known class have sufficient evidence to accept this sample?'' EGUR-A combines class-conditional local acceptance evidence with global residual evidence, and selects their relative weight from known-sample statistics without unknown validation data. Across CUB, FGVC-Aircraft, and ImageNet-hard, EGUR-A substantially reduces high-confidence false known acceptance at matched known-rejection operating points. The result is not a stronger threshold; it is a different question: whether a known class is entitled to accept a sample.
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。