USIS-PGM: Photometric Gaussian Mixtures for Underwater Salient Instance Segmentation

2026-03-14

AI Summary

This work proposes a single-stage underwater salient instance segmentation framework to address the challenges of severe boundary blurring and instance discrimination caused by underwater image degradation. The method integrates frequency-domain-aware encoding to enhance boundary details, employs a dynamic feature reweighting mechanism to adaptively refine multi-scale representations, and introduces a Transformer-based instance activation module to improve instance discriminability. Innovatively, a Photometric Gaussian Mixture (PGM) strategy is adopted to generate multi-scale Gaussian heatmaps that supervise intermediate decoder features, thereby enhancing both instance localization accuracy and mask structural consistency. Extensive experiments demonstrate that the proposed approach achieves state-of-the-art performance across multiple underwater datasets, confirming its superiority and practical value in complex underwater scenarios.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Underwater salient instance segmentation (USIS) is crucial for marine robotic systems, as it enables both underwater salient object detection and instance-level mask prediction for visual scene understanding. Compared with its terrestrial counterpart, USIS is more challenging due to the underwater image degradation. To address this issue, this paper proposes USIS-PGM, a single-stage framework for USIS. Specifically, the encoder enhances boundary cues through a frequency-aware module and performs content-adaptive feature reweighting via a dynamic weighting module. The decoder incorporates a Transformer-based instance activation module to better distinguish salient instances. In addition, USIS-PGM employs multi-scale Gaussian heatmaps generated from ground-truth masks through Photometric Gaussian Mixture (PGM) to supervise intermediate decoder features, thereby improving salient instance localization and producing more structurally coherent mask predictions. Experimental results demonstrate the superiority and practical applicability of the proposed USIS-PGM model.

Problem

• underwater salient instance segmentation
• image degradation
• instance segmentation
• salient object detection
• underwater vision

Innovation

• Photometric Gaussian Mixture
• Underwater Salient Instance Segmentation
• Frequency-aware Module
• Dynamic Weighting
• Transformer-based Instance Activation