As was mentioned before, the good thing about CornerNet is its competitive results on MS COCO dataset. Nevertheless, it has one huge drawback.
It is slow.
To overcome this issue, the authors proposed CornerNet-Lite – a combination of two efficient variants of CornerNet
1 CornerNet-Saccade: It uses an attention mechanism to avoid the need for exhaustively processing all pixels of the image
2 CornerNet-Squeeze: It introduces a new compact backbone architecture.
These two methods improve the two critical features of efficient object detection: high efficiency without sacrificing accuracy, and high accuracy at real-time efficiency (Figure 1).
如前所述,CornerNet的优点在于其在MS COCO数据集上的竞争结果。 然而,它具有一个巨大的缺点。
太慢了!
为了克服这个问题,作者提出了CornerNet-Lite – Corner CornerNet的两个有效变体的组合
- CornerNet-Saccade:它使用一种注意机制来避免彻底处理图像的所有像素的需要
- CornerNet-Squeeze:它引入了新的紧凑型主干架构。
这两