In this paper, we focus on training an open-set object detector under the condition of scarce training samples, which should distinguish the known and unknown categories. Under this challenging scenario, the decision boundaries of unknowns are difficult to learn and often ambiguous. To mitigate this issue, we develop a novel open-set object detection framework, which delves into conditional evidence decoupling for the unknown rejection. Specifically, we select pseudo-unknown samples by leveraging the discrepancy in attribution gradients between known and unknown classes, alleviating the inadequate unknown distribution coverage of training data. Subsequently, we propose a Conditional Evidence Decoupling Loss (CEDL) based on Evidential Deep Learning (EDL) theory, which decouples known and unknown properties in pseudo-unknown samples to learn distinct knowledge, enhancing separability between knowns and unknowns. Additionally, we propose an Abnormality Calibration Loss (ACL), which serves as a regularization term to adjust the output probability distribution, establishing robust decision boundaries for the unknown rejection. Our method has achieved the superiority performance over previous state-of-the-art approaches, improving the mean recall of unknown class by 7.24% across all shots in VOC10-5-5 dataset settings and 1.38% in VOC-COCO dataset settings. The code is available via https://github.com/zjzwzw/CED-FOOD.

翻译：本文聚焦于在训练样本稀缺条件下训练开放集目标检测器，该检测器需区分已知与未知类别。在此挑战性场景下，未知类别的决策边界难以学习且常具模糊性。为缓解此问题，我们提出一种新颖的开放集目标检测框架，深入探究面向未知拒斥的条件性证据解耦机制。具体而言，我们通过利用已知类与未知类在归因梯度上的差异来选取伪未知样本，从而缓解训练数据对未知分布覆盖不足的问题。随后，基于证据深度学习理论，我们提出条件性证据解耦损失函数，该函数通过解耦伪未知样本中的已知与未知属性以学习区分性知识，从而增强已知与未知类别间的可分离性。此外，我们提出异常校准损失函数作为正则化项，用于调整输出概率分布，从而为未知拒斥建立鲁棒的决策边界。本方法在多项基准测试中均优于现有先进方法，在VOC10-5-5数据集设置下所有样本量中未知类平均召回率提升7.24%，在VOC-COCO数据集设置下提升1.38%。代码已发布于https://github.com/zjzwzw/CED-FOOD。