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, e.g. biased sampling, OHEM), or use all training samples but re-weight them discriminatively (soft sampling methods, e.g. 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 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 is released at https://github.com/ChenJoya/sampling-free .

中文翻译：

---

在训练深度对象检测器时是否需要启发式采样？

为了在极端的前景-背景不平衡下训练准确的深度物体检测器，启发式采样方法总是必要的，它要么重新采样所有训练样本的子集（硬采样方法， 例如偏置采样，OHEM），或使用所有训练样本，但有区别地重新加权它们（软采样方法， 例如焦点损失，GHM）。在本文中，我们挑战了这种硬/软采样方法用于训练准确的深度物体检测器的必要性。虽然之前的研究表明，没有启发式采样方法的训练检测器会显着降低准确性，但我们发现这种降低来自不平衡导致的不合理的分类梯度幅度，而不是缺乏重新采样/重新加权。受我们发现的启发，我们提出了一种简单而有效的方法通过初始化和损失缩放实现合理的分类梯度幅度的无采样机制。与具有多个超参数的启发式采样方法不同，我们的 Sampling-Free 机制是完全数据诊断的，无需费力的超参数搜索。我们验证了我们的方法在训练基于锚点和无锚点的目标检测器方面的有效性，在 COCO 和 PASCAL VOC 数据集上，我们的方法始终比启发式采样方法实现更高的检测精度。我们的 Sampling-Free 机制为解决前景-背景不平衡问题提供了新的视角。我们的代码发布于https://github.com/ChenJoya/sampling-free .