Supplementary Material: A Transformer-Based Object Detector with Coarse-Fine Crossing Representations

The overall architecture of CFDT is shown in Figure 1. The base backbone is consistent with the network illustrated in the section of 3.1 Local-Global Cross Fusion. As shown by the red dotted lines in Figure 1, we use 100 det tokens as the additional input to perform self attention in the backbone. The det tokens dimension is also set as 256. Neck is a decoder-only modules, and there are 6 decoder layers in this neck.