RGBT Salient Object Detection: A Large-scale Dataset and Benchmark

TL;DR

This paper introduces a large-scale RGBT dataset called VT5000 and proposes a new baseline method using multi-level feature aggregation with attention, significantly advancing the state-of-the-art in RGBT salient object detection.

Contribution

The work provides the first large-scale RGBT dataset with diverse challenges and develops a novel attention-based feature aggregation method for improved detection accuracy.

Findings

The baseline method outperforms existing state-of-the-art approaches.

VT5000 dataset enables robust evaluation across various challenging scenes.

Comprehensive analysis offers insights and future research directions.

Abstract

Salient object detection in complex scenes and environments is a challenging research topic. Most works focus on RGB-based salient object detection, which limits its performance of real-life applications when confronted with adverse conditions such as dark environments and complex backgrounds. Taking advantage of RGB and thermal infrared images becomes a new research direction for detecting salient object in complex scenes recently, as thermal infrared spectrum imaging provides the complementary information and has been applied to many computer vision tasks. However, current research for RGBT salient object detection is limited by the lack of a large-scale dataset and comprehensive benchmark. This work contributes such a RGBT image dataset named VT5000, including 5000 spatially aligned RGBT image pairs with ground truth annotations. VT5000 has 11 challenges collected in different scenes and environments for exploring the robustness of algorithms. With this dataset, we propose a powerful baseline approach, which extracts multi-level features within each modality and aggregates these features of all modalities with the attention mechanism, for accurate RGBT salient object detection. Extensive experiments show that the proposed baseline approach outperforms the state-of-the-art methods on VT5000 dataset and other two public datasets. In addition, we carry out a comprehensive analysis of different algorithms of RGBT salient object detection on VT5000 dataset, and then make several valuable conclusions and provide some potential research directions for RGBT salient object detection.