SCTransNet: Spatial-Channel Cross Transformer Network for Infrared Small Target Detection

Abstract

Infrared small target detection (IRSTD) has recently benefitted greatly from U-shaped neural models. However, largely overlooking effective global information modeling, existing techniques struggle when the target has high similarities with the background. We present a {S} patial-channel {C} ross {T} ransformer Net work (SCTransNet) that leverages spatial-channel cross transformer blocks (SCTBs) on top of long-range skip connections (SKs) to address the aforementioned challenge. In the proposed SCTBs, the outputs of all encoders are interacted with cross transformer to generate mixed features, which are redistributed to all decoders to effectively reinforce semantic differences between the t..