SRSNetwork: Siamese Reconstruction-Segmentation Networks based on Dynamic-Parameter Convolution
This work addresses segmentation challenges in medical and infrared imaging, offering an incremental improvement with a novel dynamic convolution variant.
The paper tackled the problem of dynamic convolution failing in medical and infrared image segmentation due to limited data and fitting capacity, by proposing dynamic parameter convolution (DPConv) integrated into a siamese reconstruction-segmentation network, achieving superior performance on seven datasets and demonstrating generalization in zero-shot segmentation.
Dynamic convolution demonstrates outstanding representation capabilities, which are crucial for natural image segmentation. However, it fails when applied to medical image segmentation (MIS) and infrared small target segmentation (IRSTS) due to limited data and limited fitting capacity. In this paper, we propose a new type of dynamic convolution called dynamic parameter convolution (DPConv) which shows superior fitting capacity, and it can efficiently leverage features from deep layers of encoder in reconstruction tasks to generate DPConv kernels that adapt to input variations.Moreover, we observe that DPConv, built upon deep features derived from reconstruction tasks, significantly enhances downstream segmentation performance. We refer to the segmentation network integrated with DPConv generated from reconstruction network as the siamese reconstruction-segmentation network (SRS). We conduct extensive experiments on seven datasets including five medical datasets and two infrared datasets, and the experimental results demonstrate that our method can show superior performance over several recently proposed methods. Furthermore, the zero-shot segmentation under unseen modality demonstrates the generalization of DPConv. The code is available at: https://github.com/fidshu/SRSNet.