To train accurate deep object detectors under the extreme foreground-background imbalance, heuristic sampling methods are always necessary, which either re-sample a subset of all training samples (hard sampling methods, \eg biased sampling, OHEM), or use all training samples but re-weight them discriminatively (soft sampling methods, \eg Focal Loss, GHM). In this paper, we challenge the necessity of such hard/soft sampling methods for training accurate deep object detectors. While previous studies have shown that training detectors without heuristic sampling methods would significantly degrade accuracy, we reveal that this degradation comes from an unreasonable classification gradient magnitude caused by the imbalance, rather than a lack of re-sampling/re-weighting. Motivated by our discovery, we propose a simple yet effective \emph{Sampling-Free} mechanism to achieve a reasonable classification gradient magnitude by initialization and loss scaling. Unlike heuristic sampling methods with multiple hyperparameters, our Sampling-Free mechanism is fully data diagnostic, without laborious hyperparameters searching. We verify the effectiveness of our method in training anchor-based and anchor-free object detectors, where our method always achieves higher detection accuracy than heuristic sampling methods on COCO and PASCAL VOC datasets. Our Sampling-Free mechanism provides a new perspective to address the foreground-background imbalance. Our code will be released at \url{https://github.com/ChenJoya/sampling-free}.

翻译：为了在极端的地表-地下失衡状态下培训精确的深物体探测器,必须始终采用超软抽样方法,这种方法要么重新标本所有培训样本的一组(硬抽样方法,(eg)有偏差的抽样,OHEM),要么使用所有培训样本,但有区别地进行重新加权(软取样方法,(eg Cleam Loss,GHM)。在本文中,我们质疑这种硬/软取样方法对于培训精确的深物体探测器的必要性。虽然以前的研究表明,没有超温采样方法的培训探测器将大大降低准确性,但我们发现这种退化来自不平衡造成的不合理的分类梯度,而不是缺乏再抽样/再加权。我们发现后,我们提出了一个简单而有效的测试样本(emph{Samping-Free})机制,以便通过初始化和损失规模来达到合理的分类梯度程度。与具有多重超比度的超度采样采样方法不同,我们的免采样机制将完全进行数据诊断,而没有劳累的超比度计。我们核查了我们在基于固定和固定地址/固定的检测目标上培训方法的有效性。