# Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects

arXiv: https://arxiv.org/abs/1803.05082 · HTML: https://mlsanity.com/paper/1803.05082/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Mar 2018.

## Built on by (most cited first, 26 of 26)

- [Simultaneously Localize, Segment and Rank the Camouflaged Objects](https://mlsanity.com/paper/2103.04011/) (2021)
- [Salient Object Detection via Integrity Learning](https://mlsanity.com/paper/2101.07663/) (2021)
- [Advances in Deep Concealed Scene Understanding](https://mlsanity.com/paper/2304.11234/) (2023)
- [Position, Padding and Predictions: A Deeper Look at Position Information in CNNs](https://mlsanity.com/paper/2101.12322/) (2021)
- [Salient Objects in Clutter](https://mlsanity.com/paper/2105.03053/) (2021)
- [Towards Deeper Understanding of Camouflaged Object Detection](https://mlsanity.com/paper/2205.11333/) (2022)
- [Generative Transformer for Accurate and Reliable Salient Object Detection](https://mlsanity.com/paper/2104.10127/) (2021)
- [CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion](https://mlsanity.com/paper/2408.12009/) (2024)
- [Salient Object Ranking with Position-Preserved Attention](https://mlsanity.com/paper/2106.05047/) (2021)
- [Instance-Level Relative Saliency Ranking with Graph Reasoning](https://mlsanity.com/paper/2107.03824/) (2021)
- [SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness](https://mlsanity.com/paper/2108.09929/) (2021)
- [Bi-directional Object-context Prioritization Learning for Saliency Ranking](https://mlsanity.com/paper/2203.09416/) (2022)
- [Weakly-Supervised Saliency Detection via Salient Object Subitizing](https://mlsanity.com/paper/2101.00932/) (2021)
- [Rethinking Object Saliency Ranking: A Novel Whole-flow Processing Paradigm](https://mlsanity.com/paper/2312.03226/) (2023)
- [Towards Generalization in Subitizing with Neuro-Symbolic Loss using Holographic Reduced Representations](https://mlsanity.com/paper/2312.15310/) (2023)
- [Semi-supervised Salient Object Detection with Effective Confidence Estimation](https://mlsanity.com/paper/2112.14019/) (2021)
- [Pluralistic Salient Object Detection](https://mlsanity.com/paper/2409.02368/) (2024)
- [Horizontal-to-Vertical Video Conversion](https://mlsanity.com/paper/2101.04051/) (2021)
- [Modeling Long-Term Memory and Temporal Attention Shifts for Video Salient Object Ranking with a New Benchmark](https://mlsanity.com/paper/2203.17257/) (2022)
- [Semantic-guided Automatic Natural Image Matting with Trimap Generation Network and Light-weight Non-local Attention](https://mlsanity.com/paper/2103.17020/) (2021)
- [Simpler Does It: Generating Semantic Labels with Objectness Guidance](https://mlsanity.com/paper/2110.10335/) (2021)
- [A Deep Learning Framework for Visual Attention Prediction and Analysis of News Interfaces](https://mlsanity.com/paper/2503.17212/) (2025)
- [A General Divergence Modeling Strategy for Salient Object Detection](https://mlsanity.com/paper/2111.11827/) (2021)
- [Semantic Segmentation Enhanced Transformer Model for Human Attention Prediction](https://mlsanity.com/paper/2301.11022/) (2023)
- [Partitioned Saliency Ranking with Dense Pyramid Transformers](https://mlsanity.com/paper/2308.00236/) (2023)
- [Leverage Task Context for Object Affordance Ranking](https://mlsanity.com/paper/2411.16082/) (2024)

## Abstract (arXiv)

Salient object detection is a problem that has been considered in detail and many solutions proposed. In this paper, we argue that work to date has addressed a problem that is relatively ill-posed. Specifically, there is not universal agreement about what constitutes a salient object when multiple observers are queried. This implies that some objects are more likely to be judged salient than others, and implies a relative rank exists on salient objects. The solution presented in this paper solves this more general problem that considers relative rank, and we propose data and metrics suitable to measuring success in a relative object saliency landscape. A novel deep learning solution is proposed based on a hierarchical representation of relative saliency and stage-wise refinement. We also show that the problem of salient object subitizing can be addressed with the same network, and our approach exceeds performance of any prior work across all metrics considered (both traditional and newly proposed).