Unconstrained Salient Object Detection via Proposal Subset Optimization
By Jianming Zhang, Stan Sclaroff, Zhe L. Lin, Xiaohui Shen, Brian L. Price, Radomír Mech. 2016
97 citations recorded by the source corpus.
We aim at detecting salient objects in unconstrained images. In unconstrained images, the number of salient objects (if any) varies from image to image, and is not given. We present a salient object detection system that directly outputs a compact set of detection windows, if any, for an input image. Our system leverages a Convolutional-Neural-Network model to generate location proposals of salient objects. Location proposals tend to be highly overlapping and noisy. Based on the Maximum a Posteriori principle, we propose a novel subset optimization framework to generate a compact set of detection windows out of noisy proposals. In experiments, we show that our subset optimization formulation greatly enhances the performance of our system, and our system attains 16-34% relative improvement in Average Precision compared with the state-of-the-art on three challenging salient object datasets.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Ming-Ming Cheng
- Jianbing Shen
- Deng-Ping Fan
- Ling Shao
- Wenguan Wang
- Luc Van Gool
- Ali Borji
- Huchuan Lu
Citations in the corpus
- Soft-NMS — Improving Object Detection with One Line of Code (2017, methodology): “In another line of work, for detecting salient objects, a proposal subset optimization algorithm was proposed [30] as an alternative to greedy NMS.”
- Salient Object Detection in the Deep Learning Era: An In-Depth Survey (2019, methodology): “• MAP [36] emphasizes instance-level SOD in unconstrained images.”
- Instance-Level Salient Object Segmentation (2017, methodology): “f salient instance segmentation. Different colors indicate different object instances in the detected salient region. We refer to the task performed by these methods “salient region detection”, as in [51]. In this paper, we tackle a more challenging task, instance-level salient object segmentation (”
- Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground (2018, methodology): “MSR [29] was designed for both salient region detection and salient object contour detection, integrated with multi-scale combinatorial grouping and a MAPbased [35] subset optimization framework.”