UKANFormer: Noise-Robust Semantic Segmentation for Coral Reef Mapping via a Kolmogorov-Arnold Network-Transformer Hybrid
This addresses the challenge of accurate large-scale coral reef mapping for conservation efforts, where reliable labels are scarce, by showing that architectural design can mitigate label noise.
The paper tackled the problem of noisy supervision in coral reef mapping by proposing UKANFormer, a semantic segmentation model that achieved a coral-class IoU of 67.00% and pixel accuracy of 83.98%, outperforming baselines and producing more accurate predictions than the noisy labels used for training.
Coral reefs are vital yet fragile ecosystems that require accurate large-scale mapping for effective conservation. Although global products such as the Allen Coral Atlas provide unprecedented coverage of global coral reef distri-bution, their predictions are frequently limited in spatial precision and semantic consistency, especially in regions requiring fine-grained boundary delineation. To address these challenges, we propose UKANFormer, a novel se-mantic segmentation model designed to achieve high-precision mapping under noisy supervision derived from Allen Coral Atlas. Building upon the UKAN architecture, UKANFormer incorporates a Global-Local Transformer (GL-Trans) block in the decoder, enabling the extraction of both global semantic structures and local boundary details. In experiments, UKANFormer achieved a coral-class IoU of 67.00% and pixel accuracy of 83.98%, outperforming conventional baselines under the same noisy labels setting. Remarkably, the model produces predictions that are visually and structurally more accurate than the noisy labels used for training. These results challenge the notion that data quality directly limits model performance, showing that architectural design can mitigate label noise and sup-port scalable mapping under imperfect supervision. UKANFormer provides a foundation for ecological monitoring where reliable labels are scarce.