# Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss

## TL;DR

This paper introduces a novel symmetrical fully convolutional network with lossless feature reflection and a weighted structural loss for improved salient object detection, achieving superior results across multiple datasets.

## Contribution

The paper proposes a new symmetrical fully convolutional network and a weighted structural loss to enhance salient object detection accuracy and boundary clarity.

## Key findings

- Outperforms recent state-of-the-art methods on seven datasets.
- Achieves more accurate and boundary-preserving saliency maps.
- Demonstrates robustness in complex scenes.

## Abstract

Salient object detection (SOD), which aims to identify and locate the most salient pixels or regions in images, has been attracting more and more interest due to its various real-world applications. However, this vision task is quite challenging, especially under complex image scenes. Inspired by the intrinsic reflection of natural images, in this paper we propose a novel feature learning framework for large-scale salient object detection. Specifically, we design a symmetrical fully convolutional network (SFCN) to effectively learn complementary saliency features under the guidance of lossless feature reflection. The location information, together with contextual and semantic information, of salient objects are jointly utilized to supervise the proposed network for more accurate saliency predictions. In addition, to overcome the blurry boundary problem, we propose a new weighted structural loss function to ensure clear object boundaries and spatially consistent saliency. The coarse prediction results are effectively refined by these structural information for performance improvements. Extensive experiments on seven saliency detection datasets demonstrate that our approach achieves consistently superior performance and outperforms the very recent state-of-the-art methods with a large margin.