Object detection via inaccurate bounding boxes supervision has boosted a broad interest due to the expensive high-quality annotation data or the occasional inevitability of low annotation quality (\eg tiny objects). The previous works usually utilize multiple instance learning (MIL), which highly depends on category information, to select and refine a low-quality box. Those methods suffer from object drift, group prediction and part domination problems without exploring spatial information. In this paper, we heuristically propose a \textbf{Spatial Self-Distillation based Object Detector (SSD-Det)} to mine spatial information to refine the inaccurate box in a self-distillation fashion. SSD-Det utilizes a Spatial Position Self-Distillation \textbf{(SPSD)} module to exploit spatial information and an interactive structure to combine spatial information and category information, thus constructing a high-quality proposal bag. To further improve the selection procedure, a Spatial Identity Self-Distillation \textbf{(SISD)} module is introduced in SSD-Det to obtain spatial confidence to help select the best proposals. Experiments on MS-COCO and VOC datasets with noisy box annotation verify our method's effectiveness and achieve state-of-the-art performance. The code is available at https://github.com/ucas-vg/PointTinyBenchmark/tree/SSD-Det.

翻译：由于高质量标注数据成本高昂或低质量标注（如微小目标）不可避免，基于不精确边界框监督的目标检测引起了广泛关注。现有方法通常采用高度依赖类别信息的多实例学习（MIL）来筛选并优化低质量边界框。然而，这些方法因未探索空间信息，常面临目标偏移、群体预测和部分支配等问题。本文启发式地提出一种**基于空间自蒸馏的目标检测器（SSD-Det）**，通过自蒸馏方式挖掘空间信息以优化不精确边界框。SSD-Det利用**空间位置自蒸馏（SPSD）**模块挖掘空间信息，并采用交互式结构融合空间信息与类别信息，从而构建高质量候选包。为进一步优化筛选过程，SSD-Det引入**空间身份自蒸馏（SISD）**模块获取空间置信度以辅助最佳候选框选择。在带有噪声框标注的MS-COCO和VOC数据集上的实验验证了本方法的有效性，并取得了最先进的性能。代码已开源至https://github.com/ucas-vg/PointTinyBenchmark/tree/SSD-Det。