A new two-stage object detection network without RoI-Pooling

Two-stage object detection networks often propose a set of candidate boxes in the first stage, and then fine- tune the boxes in the second stage. The original two-stage object detection methods mostly process the features among the candidate boxes in the picture by RoI-Pooling [3]. Due to the overlaps of the candidate boxes proposed in the first stage, the calculation of the second stage is repetitive and the single-frame detection is slow. RoI-Pooling also makes the features of the elongated shape deformed. In this paper, we present a new two-step object detection network, called Spatial Alignment Network(SAN), which does not use the RoI-Pooling layer and reduces the computational repeatability of the second stage. We also use atrous convolution for the network fine-tuning. Our network has a competitive result, and faster than the original two-stage detectors.