Fig. 1. AF-TSD network structure

Fig. 2. Pre-processing of the input image

Fig. 3. Pipeline of deformable convolution

Fig. 4. Traditional convolution and deformable convolution

Fig. 5. Pipeline of the attention mechanism

Fig. 6. GTSDB dataset

Fig. 7. Curve of precision relative to recall rate in traffic sign detection

Fig. 8. Curve of training loss and test loss in AF-TSD network （the first 150 iterations）

Fig. 9. Traffic signs detection results