# Salient Object Ranking with Position-Preserved Attention

arXiv: https://arxiv.org/abs/2106.05047 · HTML: https://mlsanity.com/paper/2106.05047/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 57 references that are in the map.
- First posted on arXiv 9 Jun 2021.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers](https://mlsanity.com/paper/2012.00759/) (2020)
- [Learning Deep Transformer Models for Machine Translation](https://mlsanity.com/paper/1906.01787/) (2019)
- [Cascaded Partial Decoder for Fast and Accurate Salient Object Detection](https://mlsanity.com/paper/1904.08739/) (2019)
- [Exploring Visual Relationship for Image Captioning](https://mlsanity.com/paper/1809.07041/) (2018)
- [CenterMask : Real-Time Anchor-Free Instance Segmentation](https://mlsanity.com/paper/1911.06667/) (2019)
- [The Secrets of Salient Object Segmentation](https://mlsanity.com/paper/1406.2807/) (2014)
- [Deeply supervised salient object detection with short connections](https://mlsanity.com/paper/1611.04849/) (2016)
- [Salient Object Detection in the Deep Learning Era: An In-Depth Survey](https://mlsanity.com/paper/1904.09146/) (2019)
- [An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection](https://mlsanity.com/paper/1904.09730/) (2019)
- [Learning Joint Spatial-Temporal Transformations for Video Inpainting](https://mlsanity.com/paper/2007.10247/) (2020)
- [Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection](https://mlsanity.com/paper/1708.02001/) (2017)
- [Deep Contrast Learning for Salient Object Detection](https://mlsanity.com/paper/1603.01976/) (2016)
- [Learning Uncertain Convolutional Features for Accurate Saliency Detection](https://mlsanity.com/paper/1708.02031/) (2017)
- [Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects](https://mlsanity.com/paper/1803.05082/) (2018)
- [Deep Saliency with Encoded Low level Distance Map and High Level Features](https://mlsanity.com/paper/1604.05495/) (2016)
- [S4Net: Single Stage Salient-Instance Segmentation](https://mlsanity.com/paper/1711.07618/) (2017)

## Built on by (most cited first, 9 of 9)

- [Towards Deeper Understanding of Camouflaged Object Detection](https://mlsanity.com/paper/2205.11333/) (2022)
- [Spider: A Unified Framework for Context-dependent Concept Segmentation](https://mlsanity.com/paper/2405.01002/) (2024)
- [Synthetic Data Supervised Salient Object Detection](https://mlsanity.com/paper/2210.13835/) (2022)
- [Bi-directional Object-context Prioritization Learning for Saliency Ranking](https://mlsanity.com/paper/2203.09416/) (2022)
- [Rethinking Object Saliency Ranking: A Novel Whole-flow Processing Paradigm](https://mlsanity.com/paper/2312.03226/) (2023)
- [Modeling Long-Term Memory and Temporal Attention Shifts for Video Salient Object Ranking with a New Benchmark](https://mlsanity.com/paper/2203.17257/) (2022)
- [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)
- [Revisiting Salient Object Detection from an Observer-Centric Perspective](https://mlsanity.com/paper/2602.06369/) (2026)

## Abstract (arXiv)

Instance segmentation can detect where the objects are in an image, but hard to understand the relationship between them. We pay attention to a typical relationship, relative saliency. A closely related task, salient object detection, predicts a binary map highlighting a visually salient region while hard to distinguish multiple objects. Directly combining two tasks by post-processing also leads to poor performance. There is a lack of research on relative saliency at present, limiting the practical applications such as content-aware image cropping, video summary, and image labeling. In this paper, we study the Salient Object Ranking (SOR) task, which manages to assign a ranking order of each detected object according to its visual saliency. We propose the first end-to-end framework of the SOR task and solve it in a multi-task learning fashion. The framework handles instance segmentation and salient object ranking simultaneously. In this framework, the SOR branch is independent and flexible to cooperate with different detection methods, so that easy to use as a plugin. We also introduce a Position-Preserved Attention (PPA) module tailored for the SOR branch. It consists of the position embedding stage and feature interaction stage. Considering the importance of position in saliency comparison, we preserve absolute coordinates of objects in ROI pooling operation and then fuse positional information with semantic features in the first stage. In the feature interaction stage, we apply the attention mechanism to obtain proposals' contextualized representations to predict their relative ranking orders. Extensive experiments have been conducted on the ASR dataset. Without bells and whistles, our proposed method outperforms the former state-of-the-art method significantly. The code will be released publicly available.