# Weakly-Supervised Salient Object Detection Using Point Supervision

arXiv: https://arxiv.org/abs/2203.11652 · HTML: https://mlsanity.com/paper/2203.11652/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 22 Mar 2022.

## Builds on (most cited first, 26 of 26)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [What's the Point: Semantic Segmentation with Point Supervision](https://mlsanity.com/paper/1506.02106/) (2015)
- [The Secrets of Salient Object Segmentation](https://mlsanity.com/paper/1406.2807/) (2014)
- [Visual Saliency Based on Multiscale Deep Features](https://mlsanity.com/paper/1503.08663/) (2015)
- [F3Net: Fusion, Feedback and Focus for Salient Object Detection](https://mlsanity.com/paper/1911.11445/) (2019)
- [Salient Object Detection in the Deep Learning Era: An In-Depth Survey](https://mlsanity.com/paper/1904.09146/) (2019)
- [Richer Convolutional Features for Edge Detection](https://mlsanity.com/paper/1612.02103/) (2016)
- [Deep Extreme Cut: From Extreme Points to Object Segmentation](https://mlsanity.com/paper/1711.09081/) (2017)
- [Suppress and Balance: A Simple Gated Network for Salient Object Detection](https://mlsanity.com/paper/2007.08074/) (2020)
- [Reverse Attention for Salient Object Detection](https://mlsanity.com/paper/1807.09940/) (2018)
- [Normalized Cut Loss for Weakly-supervised CNN Segmentation](https://mlsanity.com/paper/1804.01346/) (2018)
- [Large-scale interactive object segmentation with human annotators](https://mlsanity.com/paper/1903.10830/) (2019)
- [Global Context-Aware Progressive Aggregation Network for Salient Object Detection](https://mlsanity.com/paper/2003.00651/) (2020)
- [Weakly-Supervised Salient Object Detection via Scribble Annotations](https://mlsanity.com/paper/2003.07685/) (2020)
- [Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence](https://mlsanity.com/paper/2012.04404/) (2020)
- [Multi-source weak supervision for saliency detection](https://mlsanity.com/paper/1904.00566/) (2019)
- [Gated CRF Loss for Weakly Supervised Semantic Image Segmentation](https://mlsanity.com/paper/1906.04651/) (2019)
- [Weakly Supervised Scene Parsing with Point-based Distance Metric Learning](https://mlsanity.com/paper/1811.02233/) (2018)
- [Weakly Supervised Salient Object Detection Using Image Labels](https://mlsanity.com/paper/1803.06503/) (2018)
- [MFNet: Multi-filter Directive Network for Weakly Supervised Salient Object Detection](https://mlsanity.com/paper/2112.01732/) (2021)
- [Saliency for Fine-grained Object Recognition in Domains with Scarce Training Data](https://mlsanity.com/paper/1808.00262/) (2018)

## Built on by (most cited first, 25 of 25)

- [Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping](https://mlsanity.com/paper/2305.11003/) (2023)
- [A Comprehensive Survey on Segment Anything Model for Vision and Beyond](https://mlsanity.com/paper/2305.08196/) (2023)
- [Weakly-Supervised Camouflaged Object Detection with Scribble Annotations](https://mlsanity.com/paper/2207.14083/) (2022)
- [Referring Image Segmentation Using Text Supervision](https://mlsanity.com/paper/2308.14575/) (2023)
- [A Simple yet Effective Network based on Vision Transformer for Camouflaged Object and Salient Object Detection](https://mlsanity.com/paper/2402.18922/) (2024)
- [Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision](https://mlsanity.com/paper/2311.14758/) (2023)
- [A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels](https://mlsanity.com/paper/2209.02957/) (2022)
- [Weakly Supervised Video Salient Object Detection via Point Supervision](https://mlsanity.com/paper/2207.07269/) (2022)
- [PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection](https://mlsanity.com/paper/2410.08210/) (2024)
- [DMSSN: Distilled Mixed Spectral-Spatial Network for Hyperspectral Salient Object Detection](https://mlsanity.com/paper/2404.00694/) (2024)
- [Point2RBox-v2: Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances](https://mlsanity.com/paper/2502.04268/) (2025)
- [SSFam: Scribble Supervised Salient Object Detection Family](https://mlsanity.com/paper/2409.04817/) (2024)
- [Wholly-WOOD: Wholly Leveraging Diversified-quality Labels for Weakly-supervised Oriented Object Detection](https://mlsanity.com/paper/2502.09471/) (2025)
- [SCALER: SAM-Enhanced Collaborative Learning for Label-Deficient Concealed Object Segmentation](https://mlsanity.com/paper/2511.18136/) (2025)
- [Segment Concealed Objects with Incomplete Supervision](https://mlsanity.com/paper/2506.08955/) (2025)
- [From Sight to Insight: Unleashing Eye-Tracking in Weakly Supervised Video Salient Object Detection](https://mlsanity.com/paper/2506.23519/) (2025)
- [Distribution-Specific Learning for Joint Salient and Camouflaged Object Detection](https://mlsanity.com/paper/2508.06063/) (2025)
- [Pixel is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detection](https://mlsanity.com/paper/2212.06493/) (2022)
- [Towards End-to-End Unsupervised Saliency Detection with Self-Supervised Top-Down Context](https://mlsanity.com/paper/2310.09533/) (2023)
- [A Point-Neighborhood Learning Framework for Nasal Endoscope Image Segmentation](https://mlsanity.com/paper/2405.20044/) (2024)
- [Spectrum-oriented Point-supervised Saliency Detector for Hyperspectral Images](https://mlsanity.com/paper/2412.18112/) (2024)
- [Synthesize Boundaries: A Boundary-aware Self-consistent Framework for Weakly Supervised Salient Object Detection](https://mlsanity.com/paper/2212.01764/) (2022)
- [A Visual Representation-guided Framework with Global Affinity for Weakly Supervised Salient Object Detection](https://mlsanity.com/paper/2302.10697/) (2023)
- [FCL-COD: Weakly Supervised Camouflaged Object Detection with Frequency-aware and Contrastive Learning](https://mlsanity.com/paper/2603.22969/) (2026)
- [CoBra: Complementary Branch Fusing Class and Semantic Knowledge for Robust Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2403.08801/) (2024)

## Abstract (arXiv)

Current state-of-the-art saliency detection models rely heavily on large datasets of accurate pixel-wise annotations, but manually labeling pixels is time-consuming and labor-intensive. There are some weakly supervised methods developed for alleviating the problem, such as image label, bounding box label, and scribble label, while point label still has not been explored in this field. In this paper, we propose a novel weakly-supervised salient object detection method using point supervision. To infer the saliency map, we first design an adaptive masked flood filling algorithm to generate pseudo labels. Then we develop a transformer-based point-supervised saliency detection model to produce the first round of saliency maps. However, due to the sparseness of the label, the weakly supervised model tends to degenerate into a general foreground detection model. To address this issue, we propose a Non-Salient Suppression (NSS) method to optimize the erroneous saliency maps generated in the first round and leverage them for the second round of training. Moreover, we build a new point-supervised dataset (P-DUTS) by relabeling the DUTS dataset. In P-DUTS, there is only one labeled point for each salient object. Comprehensive experiments on five largest benchmark datasets demonstrate our method outperforms the previous state-of-the-art methods trained with the stronger supervision and even surpass several fully supervised state-of-the-art models. The code is available at: https://github.com/shuyonggao/PSOD.