MPECAM: Multiprototype-Enhanced Weakly Supervised Segmentation Framework for Golden Tide Detection

Accurate monitoring of Golden Tides (Sargassum Harmful Algal Blooms) is critical for preventing and mitigating marine ecological disasters. Image-level weakly supervised semantic segmentation (WSSS) methods employ image-level labels to derive pixel-level predictions. While they considerably reduce annotation costs and accelerate deployment compared to fully supervised approaches, they still encounter several challenges: Golden Tide occurs as irregular floating patches at sea and class activation maps (CAMs) focus only on the most discriminative regions, many discrete targets are overlooked and pseudo-labels remain incomplete. Moreover, complex marine backgrounds distract model attention and introduce semantic noise, reducing pseudo-label reliability and hindering detection accuracy from meeting practical requirements. We propose MPECAM, a multi-prototype-enhanced weakly supervised framework for Golden Tide detection, which consists of three main components: (i) Multi-Prototype Fusion (MPF) strategy and Multi-Prototype Re-Activation (MPRA) module, which dynamically maintain a prototype bank and reweight feature maps to activate weak-response regions, thereby enhancing completeness for irregular targets; (ii) Inter-Prototype Contrastive Constraint (IC2) module, which employs a foreground-global-background triplet contrastive loss to decoupling Golden Tide feature from seawater features, suppress semantic confusion, and refine pseudo-label purity; (iii) a self-supervised consistency mechanism, which leverages the refined CAM as supervision to reintegrate structurally complete pseudo-label knowledge back into the backbone, enabling joint optimization of the modules. Experimental results on hybrid sensor remote sensing imagery covering the Yellow and East China Seas demonstrate that our method achieves state-of-the-art performance (59.25% mIoU and 74.41% F1-score), providing reliable segmentation of Golden Tide regions and offering a scalable solution for marine HAB agile monitoring.