Boundary-Aware Refinement with Environment-Robust Adapter Tuning for Underwater Instance Segmentation

Pin-Chi Pan, Soo-Chang Pei
Proceedings of the 17th Asian Conference on Machine Learning, PMLR 304:606-621, 2025.

Abstract

Underwater instance segmentation is a challenging task due to adverse visual conditions such as light attenuation, scattering, and color distortion, which severely degrade image quality and hinder model performance. In this work, we propose \\textbf\{BARD-ERA\}, a unified framework that integrates three novel components to address these challenges. First, the \\textbf\{Boundary-Aware Refinement Decoder (BARDecoder)\} improves mask quality through progressive feature refinement and lightweight upsampling using a Multi-Stage Gated Refinement Network and Depthwise Separable Upsampling. Second, the \\textbf\{Environment-Robust Adapter (ERA)\} enables efficient adaptation to underwater degradations by injecting environment-specific priors with over 90% fewer trainable parameters than full fine-tuning. Third, the \\textbf\{Boundary-Aware Cross-Entropy (BACE) loss\} enhances boundary supervision by leveraging range-null space decomposition. Together, these modules achieve state-of-the-art performance on the UIIS dataset, surpassing Mask R-CNN by 3.4 mAP with Swin-B and 3.8 mAP with ConvNeXt V2-B, while maintaining a compact model size. Our results demonstrate that BARD-ERA enables robust, accurate, and efficient segmentation in complex underwater scenes.

Cite this Paper

BibTeX
@InProceedings{pmlr-v304-pan25a, title = {Boundary-Aware Refinement with Environment-Robust Adapter Tuning for Underwater Instance Segmentation}, author = {Pan, Pin-Chi and Pei, Soo-Chang}, booktitle = {Proceedings of the 17th Asian Conference on Machine Learning}, pages = {606--621}, year = {2025}, editor = {Lee, Hung-yi and Liu, Tongliang}, volume = {304}, series = {Proceedings of Machine Learning Research}, month = {09--12 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v304/main/assets/pan25a/pan25a.pdf}, url = {https://proceedings.mlr.press/v304/pan25a.html}, abstract = {Underwater instance segmentation is a challenging task due to adverse visual conditions such as light attenuation, scattering, and color distortion, which severely degrade image quality and hinder model performance. In this work, we propose \\textbf\{BARD-ERA\}, a unified framework that integrates three novel components to address these challenges. First, the \\textbf\{Boundary-Aware Refinement Decoder (BARDecoder)\} improves mask quality through progressive feature refinement and lightweight upsampling using a Multi-Stage Gated Refinement Network and Depthwise Separable Upsampling. Second, the \\textbf\{Environment-Robust Adapter (ERA)\} enables efficient adaptation to underwater degradations by injecting environment-specific priors with over 90% fewer trainable parameters than full fine-tuning. Third, the \\textbf\{Boundary-Aware Cross-Entropy (BACE) loss\} enhances boundary supervision by leveraging range-null space decomposition. Together, these modules achieve state-of-the-art performance on the UIIS dataset, surpassing Mask R-CNN by 3.4 mAP with Swin-B and 3.8 mAP with ConvNeXt V2-B, while maintaining a compact model size. Our results demonstrate that BARD-ERA enables robust, accurate, and efficient segmentation in complex underwater scenes.} }
Endnote
%0 Conference Paper %T Boundary-Aware Refinement with Environment-Robust Adapter Tuning for Underwater Instance Segmentation %A Pin-Chi Pan %A Soo-Chang Pei %B Proceedings of the 17th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Hung-yi Lee %E Tongliang Liu %F pmlr-v304-pan25a %I PMLR %P 606--621 %U https://proceedings.mlr.press/v304/pan25a.html %V 304 %X Underwater instance segmentation is a challenging task due to adverse visual conditions such as light attenuation, scattering, and color distortion, which severely degrade image quality and hinder model performance. In this work, we propose \\textbf\{BARD-ERA\}, a unified framework that integrates three novel components to address these challenges. First, the \\textbf\{Boundary-Aware Refinement Decoder (BARDecoder)\} improves mask quality through progressive feature refinement and lightweight upsampling using a Multi-Stage Gated Refinement Network and Depthwise Separable Upsampling. Second, the \\textbf\{Environment-Robust Adapter (ERA)\} enables efficient adaptation to underwater degradations by injecting environment-specific priors with over 90% fewer trainable parameters than full fine-tuning. Third, the \\textbf\{Boundary-Aware Cross-Entropy (BACE) loss\} enhances boundary supervision by leveraging range-null space decomposition. Together, these modules achieve state-of-the-art performance on the UIIS dataset, surpassing Mask R-CNN by 3.4 mAP with Swin-B and 3.8 mAP with ConvNeXt V2-B, while maintaining a compact model size. Our results demonstrate that BARD-ERA enables robust, accurate, and efficient segmentation in complex underwater scenes.
APA
Pan, P. & Pei, S.. (2025). Boundary-Aware Refinement with Environment-Robust Adapter Tuning for Underwater Instance Segmentation. Proceedings of the 17th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 304:606-621 Available from https://proceedings.mlr.press/v304/pan25a.html.

Related Material