C²Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection

Object detection on visible (RGB) and infrared (IR) images, as an emerging solution to facilitate robust detection for around-the-clock applications, has received extensive attention in recent years. With the help of IR images, object detectors have been more reliable and robust in practical applications by using RGB-IR combined information. However, existing methods still suffer from modality miscalibration and fusion imprecision problems. Since transformer has the powerful capability to model the pairwise correlations between different features, in this article, we propose a novel Calibrated and Complementary Transformer called C²Former to address these two problems simultaneously. In C²Former, we design an intermodality cross-attention (ICA) module to obtain the calibrated and complementary features by learning the cross-attention relationship between the RGB and IR modality. To reduce the computational cost caused by computing the global attention in ICA, an adaptive feature sampling (AFS) module is introduced to decrease the dimension of feature maps. Because C²Former performs in the feature domain, it can be embedded into existing RGB-IR object detectors via the backbone network. Thus, one single-stage and one two-stage object detector both incorporating our C²Former are constructed to evaluate its effectiveness and versatility. With extensive experiments on the DroneVehicle and KAIST RGB-IR datasets, we verify that our method can fully utilize the RGB-IR complementary information and achieve robust detection results. The code is available at https://github.com/yuanmaoxun/C2Former.git.