【目标检测】小目标检测问题及解决方法

本部分主要节选自 《Augmentation for small object detection》。
针对目标检测中的小目标问题，主要有以下几种解决方法：
（1） 增加输入图片分辨率 [1,2]
（2） 混合多尺度特征 [3,4,5,6]
（3） 用 GAN 来区分大物体/小物体特征，然后对小物体特征转化为更精细的特征以此加强小目标的检测 [7]
（4） 检测小物体时增加上下文信息 [8,9,10,11]
（5） 对包含小物体的图片过采样+单张图片中多复制粘贴几份小物体 [12]

后面均是使用相关方法的参考文献，这里给出它们的名字，有兴趣的读者可以自行搜索，拓展阅读。

相关文献：
[1] 3d object proposals for accurate object class detection.
[2] Ssd: Single shot multibox detector.
[3] Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks.
[4] Feature-fused ssd: fast detection for small objects.
[5] Cnn-based small object detection and visualization with feature activation mapping.
[6] Exploit all the layers: Fast and accurate cnn object detector with scale dependent pooling and cascaded rejection classifiers.
[7] Perceptual generative adversarial networks for small object detection.
[8] R-cnn for small object detection.
[9] Loco: Local context based faster r-cnn for small traffic sign detection.
[10] Finding tiny faces.
[11] Small object detection in optical remote sensing images via modified faster r-cnn.
[12] Augmentation for small object detection