论文标题
ProbAnet：提案平衡的对象检测网络
ProbaNet: Proposal-balanced Network for Object Detection
论文作者
论文摘要
基于卷积神经网络（CNN）产生的对象探测器生成的候选对象提案会遇到易于硬的样本不平衡问题，这可能会影响整体性能。在这项研究中，我们提出了一个提案均衡的网络（ProbAnet）来减轻失衡问题。首先，ProbAnet通过通过阈值截断来丢弃简易样品来选择用于训练的硬样品的可能性。其次，ProbAnet通过增加重量来强调前景提案。为了评估证据的有效性，我们基于不同基准的训练模型。模型的平均平均精度（MAP）使用ProbAnet的平均精度（地图）比Pascal VOC 2007上的基线高1.2 $ \％$。此外，它与现有的两阶段探测器兼容，并且提供了少量的额外计算成本。
Candidate object proposals generated by object detectors based on convolutional neural network (CNN) encounter easy-hard samples imbalance problem, which can affect overall performance. In this study, we propose a Proposal-balanced Network (ProbaNet) for alleviating the imbalance problem. Firstly, ProbaNet increases the probability of choosing hard samples for training by discarding easy samples through threshold truncation. Secondly, ProbaNet emphasizes foreground proposals by increasing their weights. To evaluate the effectiveness of ProbaNet, we train models based on different benchmarks. Mean Average Precision (mAP) of the model using ProbaNet achieves 1.2$\%$ higher than the baseline on PASCAL VOC 2007. Furthermore, it is compatible with existing two-stage detectors and offers a very small amount of additional computational cost.
