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

TL;DR

This paper introduces USIS-PGM, a novel single-stage framework utilizing photometric Gaussian mixtures and Transformer-based modules to improve underwater salient instance segmentation despite challenging image conditions.

Contribution

The paper proposes a new USIS framework with a frequency-aware encoder, a Transformer-based decoder, and photometric Gaussian mixture supervision, advancing underwater salient instance segmentation.

Findings

USIS-PGM outperforms existing methods in accuracy.

The model effectively handles underwater image degradation.

Results show improved mask quality and localization.

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.