# Weakly Supervised Salient Object Detection Using Image Labels

arXiv: https://arxiv.org/abs/1803.06503 · HTML: https://mlsanity.com/paper/1803.06503/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2018.

## Built on by (most cited first, 30 of 32)

- [ADBench: Anomaly Detection Benchmark](https://mlsanity.com/paper/2206.09426/) (2022)
- [Salient Object Detection via Integrity Learning](https://mlsanity.com/paper/2101.07663/) (2021)
- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Advances in Deep Concealed Scene Understanding](https://mlsanity.com/paper/2304.11234/) (2023)
- [Weakly-Supervised Camouflaged Object Detection with Scribble Annotations](https://mlsanity.com/paper/2207.14083/) (2022)
- [MFNet: Multi-filter Directive Network for Weakly Supervised Salient Object Detection](https://mlsanity.com/paper/2112.01732/) (2021)
- [Weakly-Supervised Salient Object Detection Using Point Supervision](https://mlsanity.com/paper/2203.11652/) (2022)
- [Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images](https://mlsanity.com/paper/2104.01526/) (2021)
- [A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels](https://mlsanity.com/paper/2209.02957/) (2022)
- [Salient Objects in Clutter](https://mlsanity.com/paper/2105.03053/) (2021)
- [Generative Transformer for Accurate and Reliable Salient Object Detection](https://mlsanity.com/paper/2104.10127/) (2021)
- [Few-Cost Salient Object Detection with Adversarial-Paced Learning](https://mlsanity.com/paper/2104.01928/) (2021)
- [Unsupervised Domain Adaptive Salient Object Detection Through Uncertainty-Aware Pseudo-Label Learning](https://mlsanity.com/paper/2202.13170/) (2022)
- [Learning Debiased and Disentangled Representations for Semantic Segmentation](https://mlsanity.com/paper/2111.00531/) (2021)
- [Gaussian Dynamic Convolution for Efficient Single-Image Segmentation](https://mlsanity.com/paper/2104.08783/) (2021)
- [Synthetic Data Supervised Salient Object Detection](https://mlsanity.com/paper/2210.13835/) (2022)
- [Weakly Supervised Video Salient Object Detection via Point Supervision](https://mlsanity.com/paper/2207.07269/) (2022)
- [Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detection](https://mlsanity.com/paper/2306.03630/) (2023)
- [Energy-Based Generative Cooperative Saliency Prediction](https://mlsanity.com/paper/2106.13389/) (2021)
- [Scribble-based Boundary-aware Network for Weakly Supervised Salient Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2202.03501/) (2022)
- [Weakly-Supervised Saliency Detection via Salient Object Subitizing](https://mlsanity.com/paper/2101.00932/) (2021)
- [SSFam: Scribble Supervised Salient Object Detection Family](https://mlsanity.com/paper/2409.04817/) (2024)
- [3SD: Self-Supervised Saliency Detection With No Labels](https://mlsanity.com/paper/2203.04478/) (2022)
- [Semi-supervised Salient Object Detection with Effective Confidence Estimation](https://mlsanity.com/paper/2112.14019/) (2021)
- [To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection](https://mlsanity.com/paper/2109.01770/) (2021)
- [Pixel is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detection](https://mlsanity.com/paper/2212.06493/) (2022)
- [Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization](https://mlsanity.com/paper/2309.01331/) (2023)
- [Salient Object Detection via Bounding-box Supervision](https://mlsanity.com/paper/2205.05245/) (2022)
- [A Visual Representation-guided Framework with Global Affinity for Weakly Supervised Salient Object Detection](https://mlsanity.com/paper/2302.10697/) (2023)
- [Learning Video Salient Object Detection Progressively from Unlabeled Videos](https://mlsanity.com/paper/2204.02008/) (2022)

## Abstract (arXiv)

Deep learning based salient object detection has recently achieved great success with its performance greatly outperforms any other unsupervised methods. However, annotating per-pixel saliency masks is a tedious and inefficient procedure. In this paper, we note that superior salient object detection can be obtained by iteratively mining and correcting the labeling ambiguity on saliency maps from traditional unsupervised methods. We propose to use the combination of a coarse salient object activation map from the classification network and saliency maps generated from unsupervised methods as pixel-level annotation, and develop a simple yet very effective algorithm to train fully convolutional networks for salient object detection supervised by these noisy annotations. Our algorithm is based on alternately exploiting a graphical model and training a fully convolutional network for model updating. The graphical model corrects the internal labeling ambiguity through spatial consistency and structure preserving while the fully convolutional network helps to correct the cross-image semantic ambiguity and simultaneously update the coarse activation map for next iteration. Experimental results demonstrate that our proposed method greatly outperforms all state-of-the-art unsupervised saliency detection methods and can be comparable to the current best strongly-supervised methods training with thousands of pixel-level saliency map annotations on all public benchmarks.