DRPN: Making CNN Dynamically Handle Scale Variation
This addresses scale variation issues in infrared datasets for detection tasks, representing an incremental improvement over existing methods like SKNet or TridentNet.
The paper tackles scale variation in infrared target detection by proposing a dynamic re-parameterization network (DRPN) that adaptively adjusts receptive fields, achieving state-of-the-art performance on datasets like FLIR, KAIST, and InfraPlane.
Based on our observations of infrared targets, serious scale variation along within sequence frames has high-frequently occurred. In this paper, we propose a dynamic re-parameterization network (DRPN) to deal with the scale variation and balance the detection precision between small targets and large targets in infrared datasets. DRPN adopts the multiple branches with different sizes of convolution kernels and the dynamic convolution strategy. Multiple branches with different sizes of convolution kernels have different sizes of receptive fields. Dynamic convolution strategy makes DRPN adaptively weight multiple branches. DRPN can dynamically adjust the receptive field according to the scale variation of the target. Besides, in order to maintain effective inference in the test phase, the multi-branch structure is further converted to a single-branch structure via the re-parameterization technique after training. Extensive experiments on FLIR, KAIST, and InfraPlane datasets demonstrate the effectiveness of our proposed DRPN. The experimental results show that detectors using the proposed DRPN as the basic structure rather than SKNet or TridentNet obtained the best performances.