In recent years, a number of detectors have been proposed to improve the accuracy and speed of object detection tasks. However, poor detection performances for small objects and difficulties in optimizing deep networks remain critical challenges for object detection. We try to tackle these problems in two ways. First, we propose an innovative cross-fusion block (CFB) module that can enhance the representational power of features for instances of small objects. In CFBs, high-level features with rich semantic information and low-level features from different layers at the same scale are cross-fused together. Second, we propose a periodic oscillation attenuation learning rate (POA_lr) that can effectively skip some purely locally optimal solutions in the training process to obtain better detection accuracy. Extensive experiments on PASCAL VOC and MS COCO datasets show that CFB and POA_lr can achieve higher detection accuracy while maintaining real-time processing speeds. The code will be made publicly available.

中文翻译：

---

功能交叉融合的块状网，可实现准确有效的目标检测

近年来，已经提出了许多检测器以提高物体检测任务的准确性和速度。然而，对于小物体的不良检测性能以及优化深度网络的困难仍然是物体检测的关键挑战。我们尝试以两种方式解决这些问题。首先，我们提出了一种创新的交叉融合块（CFB）模块，该模块可以增强小对象实例的要素表示能力。在CFB中，具有丰富语义信息的高级功能和来自同一级别不同层的低级功能被交叉融合在一起。其次，我们提出了一种周期性的振荡衰减学习率（POA_1r），可以在训练过程中有效地跳过一些纯粹的局部最优解，以获得更好的检测精度。在PASCAL VOC和MS COCO数据集上进行的大量实验表明，CFB和POA_lr可以在保持实时处理速度的同时实现更高的检测精度。该代码将公开提供。