Mirror Feature-Aware Generative Adversarial Network for RGB-T Salient Object Detection

Existing RGB-T salient object detection methods often employ asymmetric feature processing mechanisms, which lead to limited inter-modal interaction and difficulties in achieving cross-modal semantic alignment. Moreover, due to the inherent differences in imaging mechanisms, modality conflicts caused by feature prior mismatches severely restrict the efficient exploitation of complementary information. To address these challenges, we propose a Mirror Feature-aware Generative Adversarial Network (MFAGAN). We introduce adversarial learning into the multi-modal feature fusion process, transforming the implicit feature alignment assumptions in traditional fusion methods into explicit distribution consistency constraints through the dynamic game mechanism between the generator and discriminator. Specifically, MFAGAN designs a triple collaborative optimization component: 1) A symmetric two-stage encoder achieves a dynamic balance between pixel-level details and semantic-level representations through bidirectional alternating guidance; 2) A cross-modal residual decoder employs independent parameter paths to preserve modality-specific characteristics and suppress fusion bias; 3) A feature difference complementation module adaptively integrates differential information from regions with confidence conflicts. We conduct extensive experiments on three public datasets. The experimental results show that the MFAGAN achieves better performance than the competing methods. Codes and results are released on https://github.com/asd291614761/MFAGAN.