# DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection

arXiv: https://arxiv.org/abs/1510.05484 · HTML: https://mlsanity.com/paper/1510.05484/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2015.

## Built on by (most cited first, 24 of 24)

- [Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Models](https://mlsanity.com/paper/2105.08127/) (2021)
- [Densely Nested Top-Down Flows for Salient Object Detection](https://mlsanity.com/paper/2102.09133/) (2021)
- [Salient Objects in Clutter](https://mlsanity.com/paper/2105.03053/) (2021)
- [Sketch2Saliency: Learning to Detect Salient Objects from Human Drawings](https://mlsanity.com/paper/2303.11502/) (2023)
- [Sequential vessel segmentation via deep channel attention network](https://mlsanity.com/paper/2102.05229/) (2021)
- [Deep Learning-based Occluded Person Re-identification: A Survey](https://mlsanity.com/paper/2207.14452/) (2022)
- [Position-Aware Relation Learning for RGB-Thermal Salient Object Detection](https://mlsanity.com/paper/2209.10158/) (2022)
- [GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector](https://mlsanity.com/paper/2205.15469/) (2022)
- [Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations](https://mlsanity.com/paper/2103.12719/) (2021)
- [Learning to Transfer for Traffic Forecasting via Multi-task Learning](https://mlsanity.com/paper/2111.15542/) (2021)
- [Task-Adaptive Meta-Learning Framework for Advancing Spatial Generalizability](https://mlsanity.com/paper/2212.06864/) (2022)
- [Weakly-Supervised Saliency Detection via Salient Object Subitizing](https://mlsanity.com/paper/2101.00932/) (2021)
- [A Mutual Learning Method for Salient Object Detection with intertwined Multi-Supervision--Revised](https://mlsanity.com/paper/2509.21363/) (2025)
- [Balanced Classification: A Unified Framework for Long-Tailed Object Detection](https://mlsanity.com/paper/2308.02213/) (2023)
- [Target Detection and Segmentation in Circular-Scan Synthetic-Aperture-Sonar Images using Semi-Supervised Convolutional Encoder-Decoders](https://mlsanity.com/paper/2101.03603/) (2021)
- [Identity and Posture Recognition in Smart Beds with Deep Multitask Learning](https://mlsanity.com/paper/2104.02159/) (2021)
- [RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradation](https://mlsanity.com/paper/2609.12622/) (2026)
- [LC3Net: Ladder context correlation complementary network for salient object detection](https://mlsanity.com/paper/2110.10869/) (2021)
- [Generalized Task-Driven Medical Image Quality Enhancement with Gradient Promotion](https://mlsanity.com/paper/2501.01114/) (2025)
- [Digital-twin-enhanced metal tube bending forming real-time prediction method based on Multi-source-input MTL](https://mlsanity.com/paper/2207.00961/) (2022)
- [β-Multivariational Autoencoder for Entangled Representation Learning in Video Frames](https://mlsanity.com/paper/2211.12627/) (2022)
- [Towards Size-invariant Salient Object Detection: A Generic Evaluation and Optimization Approach](https://mlsanity.com/paper/2509.15573/) (2025)
- [A review of Recent Techniques for Person Re-Identification](https://mlsanity.com/paper/2509.22690/) (2025)
- [A Study on Real-time Object Detection using Deep Learning](https://mlsanity.com/paper/2602.15926/) (2026)

## Abstract (arXiv)

A key problem in salient object detection is how to effectively model the semantic properties of salient objects in a data-driven manner. In this paper, we propose a multi-task deep saliency model based on a fully convolutional neural network (FCNN) with global input (whole raw images) and global output (whole saliency maps). In principle, the proposed saliency model takes a data-driven strategy for encoding the underlying saliency prior information, and then sets up a multi-task learning scheme for exploring the intrinsic correlations between saliency detection and semantic image segmentation. Through collaborative feature learning from such two correlated tasks, the shared fully convolutional layers produce effective features for object perception. Moreover, it is capable of capturing the semantic information on salient objects across different levels using the fully convolutional layers, which investigate the feature-sharing properties of salient object detection with great feature redundancy reduction. Finally, we present a graph Laplacian regularized nonlinear regression model for saliency refinement. Experimental results demonstrate the effectiveness of our approach in comparison with the state-of-the-art approaches.