USIS16K: High-Quality Dataset for Underwater Salient Instance Segmentation

TL;DR

This paper introduces USIS16K, a large-scale, high-quality dataset for underwater salient instance segmentation, addressing the lack of data and benchmarks in this challenging environment.

Contribution

The paper provides the first large-scale, diverse dataset with high-quality annotations for underwater salient instance segmentation and offers benchmark evaluations for future research.

Findings

USIS16K contains 16,151 annotated underwater images across 158 categories.

Benchmark results establish baseline performance for underwater object detection and segmentation.

The dataset enhances research potential in underwater computer vision applications.

Abstract

Inspired by the biological visual system that selectively allocates attention to efficiently identify salient objects or regions, underwater salient instance segmentation (USIS) aims to jointly address the problems of where to look (saliency prediction) and what is there (instance segmentation) in underwater scenarios. However, USIS remains an underexplored challenge due to the inaccessibility and dynamic nature of underwater environments, as well as the scarcity of large-scale, high-quality annotated datasets. In this paper, we introduce USIS16K, a large-scale dataset comprising 16,151 high-resolution underwater images collected from diverse environmental settings and covering 158 categories of underwater objects. Each image is annotated with high-quality instance-level salient object masks, representing a significant advance in terms of diversity, complexity, and scalability. Furthermore, we provide benchmark evaluations on underwater object detection and USIS tasks using USIS16K. To facilitate future research in this domain, the dataset and benchmark models are publicly available.