Wavelet-Enhanced Cross-Strip Network for Remote Sensing Object Detection

Recently, remote sensing object detection (RSOD) still faces challenges, especially in scenarios involving multi-scale, small, and elongated objects. To address these issues, we propose the wavelet-enhanced cross-strip network, a novel backbone network specifically designed for RSOD. First, we design a Multi-scale Cross-Strip Convolution (MCSConv) module by integrating the local contextual capability of square convolutions with the anisotropic modeling advantages of strip convolutions, thereby forming a mixed square-strip receptive field. This design successfully captures directional features of elongated targets while significantly alleviating feature redundancy. Concurrently, its channel-adaptive weighting mechanism further enhances the representation capability for multi-scale targets. Furthermore, we introduce a High-Low Frequency Feature Enhancement (HLFE) module to decompose feature maps into low- and high-frequency components via the discrete Haar wavelet transform (DWT). A High-Frequency Denoising Enhancement (HFDE) module suppresses noise and enhances edge textures in high-frequency components to preserve crucial information of small objects in the shallow layers, while Gaussian convolution enhances low-frequency semantics to highlight global structures and object contours in the deep layers. Comprehensive evaluations on four benchmarks (DOTA-v1.0, DOTA-v1.5, DIOR-R, and FAIR1M1.0) verify that WECSNet achieves highly competitive detection performance with fewer parameters.