Object Detection Based on Swin Deformable Transformer-BiPAFPN-YOLOX

<div>Reconstructed Deformable Self-Attention. Red boxes depict windows, gray boxes are patches, and blue dots are patch grid points. Red, purple, yellow, and green regions represent regions of importance, showing that the patch grid points move to important regions.</div>

Computational Intelligence and Neuroscience

fig2

Figure 2

Figure 2: Object Detection Based on Swin Deformable Transformer-BiPAFPN-YOLOX 