CAFC-Net: A Critical and Align Feature Constructing Network for Oriented Ship Detection in Aerial Images

<table class="table-group" id="tab4"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left"> Methods</td><td class="align_center">mAP (%)</td><td class="align_center">Speed (ms)</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">Conv</td><td class="align_center">87.48</td><td class="align_center">35</td></tr><tr><td class="align_left">DeformConv</td><td class="align_center">88.68</td><td class="align_center">37</td></tr><tr><td class="align_left">DeformConv v2</td><td class="align_center">89.88</td><td class="align_center">38</td></tr><tr><td class="align_left">AlignConv</td><td class="align_center">91.18</td><td class="align_center">39</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Comparison of AlignConv with other convolution methods.</div>

Computational Intelligence and Neuroscience

tab4

Table 4

Table 4: CAFC-Net: A Critical and Align Feature Constructing Network for Oriented Ship Detection in Aerial Images 