# Salient Object Detection with Purificatory Mechanism and Structural Similarity Loss

arXiv: https://arxiv.org/abs/1912.08393 · HTML: https://mlsanity.com/paper/1912.08393/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2019.

## Built on by (most cited first, 14 of 14)

- [Democracy Does Matter: Comprehensive Feature Mining for Co-Salient Object Detection](https://mlsanity.com/paper/2203.05787/) (2022)
- [RGB-D Salient Object Detection with Ubiquitous Target Awareness](https://mlsanity.com/paper/2109.03425/) (2021)
- [Unsupervised and semi-supervised co-salient object detection via segmentation frequency statistics](https://mlsanity.com/paper/2311.06654/) (2023)
- [View-aware Salient Object Detection for 360deg Omnidirectional Image](https://mlsanity.com/paper/2209.13222/) (2022)
- [Part-Whole Relational Fusion Towards Multi-Modal Scene Understanding](https://mlsanity.com/paper/2410.14944/) (2024)
- [Salient Object Detection via Dynamic Scale Routing](https://mlsanity.com/paper/2210.13821/) (2022)
- [Rethinking Lightweight Salient Object Detection via Network Depth-Width Tradeoff](https://mlsanity.com/paper/2301.06679/) (2023)
- [Pluralistic Salient Object Detection](https://mlsanity.com/paper/2409.02368/) (2024)
- [KD-SCFNet: Towards More Accurate and Efficient Salient Object Detection via Knowledge Distillation](https://mlsanity.com/paper/2208.02178/) (2022)
- [Sharp Eyes: A Salient Object Detector Working The Same Way as Human Visual Characteristics](https://mlsanity.com/paper/2301.07431/) (2023)
- [Self-supervised co-salient object detection via feature correspondence at multiple scales](https://mlsanity.com/paper/2403.11107/) (2024)
- [TDFNet: Tri-projection Deformable Fusion Network for Panoramic Salient Object Detection](https://mlsanity.com/paper/2608.25808/) (2026)
- [Towards Size-invariant Salient Object Detection: A Generic Evaluation and Optimization Approach](https://mlsanity.com/paper/2509.15573/) (2025)
- [MIMONet: Multi-scale Input and Multi-scale Output Network for Salient Object Detection](https://mlsanity.com/paper/2608.25733/) (2026)

## Abstract (arXiv)

By the aid of attention mechanisms to weight the image features adaptively, recent advanced deep learning-based models encourage the predicted results to approximate the ground-truth masks with as large predictable areas as possible, thus achieving the state-of-the-art performance. However, these methods do not pay enough attention to small areas prone to misprediction. In this way, it is still tough to accurately locate salient objects due to the existence of regions with indistinguishable foreground and background and regions with complex or fine structures. To address these problems, we propose a novel convolutional neural network with purificatory mechanism and structural similarity loss. Specifically, in order to better locate preliminary salient objects, we first introduce the promotion attention, which is based on spatial and channel attention mechanisms to promote attention to salient regions. Subsequently, for the purpose of restoring the indistinguishable regions that can be regarded as error-prone regions of one model, we propose the rectification attention, which is learned from the areas of wrong prediction and guide the network to focus on error-prone regions thus rectifying errors. Through these two attentions, we use the Purificatory Mechanism to impose strict weights with different regions of the whole salient objects and purify results from hard-to-distinguish regions, thus accurately predicting the locations and details of salient objects. In addition to paying different attention to these hard-to-distinguish regions, we also consider the structural constraints on complex regions and propose the Structural Similarity Loss. In experiments, the proposed approach outperforms 19 state-of-the-art methods on six datasets with a notable margin at over 27FPS on a single NVIDIA 1080Ti GPU.