A wavelet-decoupled complementarity-guided expert network (WCGE-Net), whose core idea is to combine wavelet-based frequency disentanglement with mixture-of-experts (MoE) to progressively decouple, calibrate, and integrate complementary features for high-fidelity reconstruction.
Yan Mou, Zhao-Long Gao, Yan-Yan Mao et al.· IEEE Journal of Selected Top...· 0 citations
The proposed LTS-ProtoNet effectively improves the completeness of changed regions, boundary localization accuracy, and multiscale target detection stability in complex scenes, achieving competitive detection performance.
This paper introduces a novel underwater salient object detection framework based on an information cross-fusion network that achieves superior performance compared to state-of-the-art approaches, highlighting its efficacy in multimodal feature integration and salient object detection.
Yan Mou, Zhao-Long Gao, Jinjiang Li· PLoS ONE· 0 citations
A discrepancy-invariant recalibration module is proposed, which explicitly utilizes invariant features between different time phases to calibrate the difference features and enhance the ability to suppress false changes.
A cross-stage state refiner is introduced to progressively refine multilevel features by integrating the input features with the outputs of different stages through state-aware gated normalization, and a weighted feature pyramid decoder performs top-down fusion of the refined hierarchical features.
Zeyu Zhao, Zhao-Long Gao, Jun Feng· IEEE Journal of Selected Top...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
