# PAANet:Visual Perception based Four-stage Framework for Salient Object Detection using High-order Contrast Operator

arXiv: https://arxiv.org/abs/2211.08724 · HTML: https://mlsanity.com/paper/2211.08724/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 16 Nov 2022.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://mlsanity.com/paper/2005.09007/) (2020)
- [Enhanced-alignment Measure for Binary Foreground Map Evaluation](https://mlsanity.com/paper/1805.10421/) (2018)
- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [Cascaded Partial Decoder for Fast and Accurate Salient Object Detection](https://mlsanity.com/paper/1904.08739/) (2019)
- [A Simple Pooling-Based Design for Real-Time Salient Object Detection](https://mlsanity.com/paper/1904.09569/) (2019)
- [The Secrets of Salient Object Segmentation](https://mlsanity.com/paper/1406.2807/) (2014)
- [Deeply supervised salient object detection with short connections](https://mlsanity.com/paper/1611.04849/) (2016)
- [Visual Saliency Based on Multiscale Deep Features](https://mlsanity.com/paper/1503.08663/) (2015)
- [Reverse Attention for Salient Object Detection](https://mlsanity.com/paper/1807.09940/) (2018)
- [Label Decoupling Framework for Salient Object Detection](https://mlsanity.com/paper/2008.11048/) (2020)
- [Global Context-Aware Progressive Aggregation Network for Salient Object Detection](https://mlsanity.com/paper/2003.00651/) (2020)
- [Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection](https://mlsanity.com/paper/1708.02001/) (2017)
- [Multi-label Image Recognition by Recurrently Discovering Attentional Regions](https://mlsanity.com/paper/1711.02816/) (2017)
- [STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation](https://mlsanity.com/paper/1509.03150/) (2015)
- [Deep Visual Attention Prediction](https://mlsanity.com/paper/1705.02544/) (2017)
- [Learning Uncertain Convolutional Features for Accurate Saliency Detection](https://mlsanity.com/paper/1708.02031/) (2017)
- [Multi-source weak supervision for saliency detection](https://mlsanity.com/paper/1904.00566/) (2019)
- [Visual Saliency Detection Based on Multiscale Deep CNN Features](https://mlsanity.com/paper/1609.02077/) (2016)
- [Top-Down Saliency Detection Driven by Visual Classification](https://mlsanity.com/paper/1709.05307/) (2017)
- [Saliency Guided End-to-End Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1706.06768/) (2017)

## Abstract (arXiv)

It is believed that human vision system (HVS) consists of pre-attentive process and attention process when performing salient object detection (SOD). Based on this fact, we propose a four-stage framework for SOD, in which the first two stages match the Pre-Attentive process consisting of general feature extraction (GFE) and feature preprocessing (FP), and the last two stages are corresponding to Attention process containing saliency feature extraction (SFE) and the feature aggregation (FA), namely PAANet. According to the pre-attentive process, the GFE stage applies the fully-trained backbone and needs no further finetuning for different datasets. This modification can greatly increase the training speed. The FP stage plays the role of finetuning but works more efficiently because of its simpler structure and fewer parameters. Moreover, in SFE stage we design for saliency feature extraction a novel contrast operator, which works more semantically in contrast with the traditional convolution operator when extracting the interactive information between the foreground and its surroundings. Interestingly, this contrast operator can be cascaded to form a deeper structure and extract higher-order saliency more effective for complex scene. Comparative experiments with the state-of-the-art methods on 5 datasets demonstrate the effectiveness of our framework.