论文标题
未知的对象检测：从野外视频中了解您不知道的知识
Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild
论文作者
论文摘要
构建可以检测到分布（OOD）对象的可靠对象探测器至关重要但尚未得到充满震撼。关键挑战之一是，模型缺乏来自未知数据的监督信号，从而产生了对OOD对象的过度自信预测。我们通过时空未知的蒸馏（螺柱）提出了一个新的未知对象检测框架，该框架将未知的对象从野外视频中提取，并有意义地将模型的决策边界定向。 Stud首先在空间维度中标识未知的候选对象建议，然后将候选者跨多个视频帧汇总，以形成决策边界附近的一组未知对象。在旁边，我们采用了基于能量的不确定性正则化损失，该损失对形成了分布和蒸馏的未知物体之间的不确定性空间。与以前的最佳方法相比，Stud在OOD检测任务上建立了最先进的性能，将FPR95分数降低了10％以上。代码可在https://github.com/deeplearning-wisc/stud上找到。
Building reliable object detectors that can detect out-of-distribution (OOD) objects is critical yet underexplored. One of the key challenges is that models lack supervision signals from unknown data, producing overconfident predictions on OOD objects. We propose a new unknown-aware object detection framework through Spatial-Temporal Unknown Distillation (STUD), which distills unknown objects from videos in the wild and meaningfully regularizes the model's decision boundary. STUD first identifies the unknown candidate object proposals in the spatial dimension, and then aggregates the candidates across multiple video frames to form a diverse set of unknown objects near the decision boundary. Alongside, we employ an energy-based uncertainty regularization loss, which contrastively shapes the uncertainty space between the in-distribution and distilled unknown objects. STUD establishes the state-of-the-art performance on OOD detection tasks for object detection, reducing the FPR95 score by over 10% compared to the previous best method. Code is available at https://github.com/deeplearning-wisc/stud.
