WXSOD: A Benchmark for Robust Salient Object Detection in Adverse Weather Conditions

2025-08-17

AI Summary

Significant performance degradation of salient object detection (SOD) under adverse weather conditions, coupled with the absence of high-quality benchmark datasets, motivates this work. To address this, we introduce WXSOD—the first pixel-level annotated SOD dataset specifically designed for weather interference—comprising 14,945 images spanning diverse real and synthetic weather degradations, accompanied by fine-grained weather labels and separate real/synthetic test splits. We further propose WFANet, a weather-aware feature aggregation network featuring a fully supervised dual-branch architecture that jointly predicts weather categories and saliency maps, leveraging deep feature fusion to co-model semantic and weather-correlated cues. Comprehensive evaluation on WXSOD demonstrates that WFANet outperforms 17 state-of-the-art SOD methods by a substantial margin, validating its superior robustness and generalization capability in complex, weather-degraded scenes.

Technology Category

• Computer Vision: Object Detection & Categorization
• Machine Learning: Hardware-aware ML
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Salient object detection (SOD) in complex environments remains a challenging research topic. Most existing methods perform well in natural scenes with negligible noise, and tend to leverage multi-modal information (e.g., depth and infrared) to enhance accuracy. However, few studies are concerned with the damage of weather noise on SOD performance due to the lack of dataset with pixel-wise annotations. To bridge this gap, this paper introduces a novel Weather-eXtended Salient Object Detection (WXSOD) dataset. It consists of 14,945 RGB images with diverse weather noise, along with the corresponding ground truth annotations and weather labels. To verify algorithm generalization, WXSOD contains two test sets, i.e., a synthesized test set and a real test set. The former is generated by adding weather noise to clean images, while the latter contains real-world weather noise. Based on WXSOD, we propose an efficient baseline, termed Weather-aware Feature Aggregation Network (WFANet), which adopts a fully supervised two-branch architecture. Specifically, the weather prediction branch mines weather-related deep features, while the saliency detection branch fuses semantic features extracted from the backbone with weather features for SOD. Comprehensive comparisons against 17 SOD methods shows that our WFANet achieves superior performance on WXSOD. The code and benchmark results will be made publicly available at https://github.com/C-water/WXSOD

Problem

• Lack of dataset for SOD in adverse weather
• Need robust SOD methods for weather noise
• Propose WFANet to fuse weather and saliency features

Innovation

• Introduces WXSOD dataset with weather noise
• Proposes WFANet with two-branch architecture
• Mines weather features for saliency detection