A method of detecting at least one element of interest visible on an input image, by means of a convolutional neural network, CNN, the method comprises the steps of: (a) extracting, by means of an ascending branch of a first subnetwork of said CNN of feature pyramid network, FPN, type, a plurality of initial feature maps (C1, C2, C3, C4, C5) representative of the input image at different scales, said FPN further comprising a descending branch and lateral connections between the ascending branch and the descending branch, at least one lateral connection comprising an attention module; (b) generating, by means of said descending branch of the FPN, a plurality of enriched feature maps (P2, P3, P4, P5) also representative of the input image at different scales, each enriched feature map (P2, P3, P4, P5) incorporating the information from the initial feature maps (C1, C2, C3, C4, C5) of smaller or equal scale; (d) detecting at least one element of interest visible on an input image, by means of a second subnetwork of said CNN, referred to as detection network, taking said enriched feature maps (P2, P3, P4, P5) as input.