AI 中文总结
本研究审计冻结CLIP区域解释的最坏干扰特异性，发现大量区域对竞争类别贡献过高，并提出在容忍度约束下利用替代区域进行修复的有限可能性。
AI 中文摘要
一个区域可能与目标对象重叠，却对另一个类别贡献更大。我们测试了冻结CLIP中基于簇的概念重要性（CCI）所选择的区域。在COCO和VOC两个数据集上，使用两个检查点，通过重叠和平均对比检查的区域中有41.08%-64.78%在最强竞争类别下失败。移除图像中标注的竞争者后，仍有39.69%-63.64%失败。随后我们测试了每张图像的所有八个候选区域。在COCO上，替代区域通过测试的比例为失败案例的6.25%-7.84%，在VOC上为27.40%-31.15%。要求其在ε=0.02内保持原始目标分数下降，将这些比例降至0.16%-0.98%。可用区域和目标分数下降容忍度限制了修复；放宽容忍度会增加修复机会。
英文摘要
A region can overlap a target object yet contribute more to another class. We test regions selected by Cluster-based Concept Importance (CCI) in frozen CLIP. Across COCO and VOC with two checkpoints, 41.08-64.78% of regions that pass overlap and mean-contrast checks fail against the strongest competing class. Removing competitors annotated in the image leaves 39.69-63.64% failing. We then test all eight candidate regions per image. An alternative passes the test for 6.25-7.84% of failures on COCO and 27.40-31.15% on VOC. Requiring it to preserve the original target-score drop within $ε= 0.02$ reduces these rates to 0.16-0.98%. Available regions and target-drop tolerance constrain repair; relaxing the tolerance increases repair opportunities.
Comments5 pages, 2 figures, 6 tables
