# Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection

arXiv: https://arxiv.org/abs/1909.04366 · HTML: https://mlsanity.com/paper/1909.04366/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2019.

## Built on by (most cited first, 11 of 11)

- [Salient Object Detection via Integrity Learning](https://mlsanity.com/paper/2101.07663/) (2021)
- [Salient Objects in Clutter](https://mlsanity.com/paper/2105.03053/) (2021)
- [Towards Diverse Binary Segmentation via A Simple yet General Gated Network](https://mlsanity.com/paper/2303.10396/) (2023)
- [Learning to Detect Instance-level Salient Objects Using Complementary Image Labels](https://mlsanity.com/paper/2111.10137/) (2021)
- [Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net](https://mlsanity.com/paper/2108.07851/) (2021)
- [Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction](https://mlsanity.com/paper/2101.02843/) (2021)
- [TS-SAM: Fine-Tuning Segment-Anything Model for Downstream Tasks](https://mlsanity.com/paper/2408.01835/) (2024)
- [Variational Structured Attention Networks for Deep Visual Representation Learning](https://mlsanity.com/paper/2103.03510/) (2021)
- [Bones Can't Be Triangles: Accurate and Efficient Vertebrae Keypoint Estimation through Collaborative Error Revision](https://mlsanity.com/paper/2409.03261/) (2024)
- [Are Large Vision-Language Models Ready to Guide Blind and Low-Vision Individuals?](https://mlsanity.com/paper/2510.00766/) (2025)
- [How Blind and Low-Vision Individuals Prefer Large Vision-Language Model-Generated Scene Descriptions](https://mlsanity.com/paper/2502.14883/) (2025)

## Abstract (arXiv)

Recent saliency models extensively explore to incorporate multi-scale contextual information from Convolutional Neural Networks (CNNs). Besides direct fusion strategies, many approaches introduce message-passing to enhance CNN features or predictions. However, the messages are mainly transmitted in two ways, by feature-to-feature passing, and by prediction-to-prediction passing. In this paper, we add message-passing between features and predictions and propose a deep unified CRF saliency model . We design a novel cascade CRFs architecture with CNN to jointly refine deep features and predictions at each scale and progressively compute a final refined saliency map. We formulate the CRF graphical model that involves message-passing of feature-feature, feature-prediction, and prediction-prediction, from the coarse scale to the finer scale, to update the features and the corresponding predictions. Also, we formulate the mean-field updates for joint end-to-end model training with CNN through back propagation. The proposed deep unified CRF saliency model is evaluated over six datasets and shows highly competitive performance among the state of the arts.