Learning Nonlinear Feature Mapping via Constrained Non-Convex Optimization for Unsupervised Salient Object Detection

Wang, Shigang

doi:10.1109/access.2022.3166986

Cited by 3 publications

(1 citation statement)

References 47 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, visual attention works both in a top-down task driven and bottom-up scene stimulated manner. Ever since the pioneer work of Itti et al [4], there has been an increasing interest in predicting this saliency map with computer algorithms [5]- [7]. Also, the advancement of saliency modeling technique has benefited a wide range of scientific and engineering fields, such as industrial defect detection [8], remote sensing interpretation [9], multi-media applications [10], etc.…”

Section: Introductionmentioning

confidence: 99%

Joint Learning of Discriminative Metric Space From Multi-Context Visual Scene for Unsupervised Salient Object Detection

Wang

2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

Mimicking the biological visual attention mechanism to discriminate visually appealing regions in natural scenes has been a hot research topic in recent years. However, designing computational models with self-driven capability for open world scenarios remains a challenging task which deserves to be further studied. In this paper, we propose an unsupervised learning approach to detect salient objects from images by fully exploiting the multi-context semantic information of the scenes. Specifically, a selfdriven model combing the idea of discriminative metric learning and structured sparse constraint is designed to find an optimal semantic mapping space for robust scene specific saliency prediction from complex environments. Meanwhile, a heuristic alternating optimization algorithm is developed to remove the ambiguity in the coarse geometric prior to generate a fine-grained discriminative model for saliency. On the basis of this, multi-context visual scenes are jointly modeled and fused to capture the image hierarchical structures for high-quality saliency map generation. Finally, we conduct experiments to verify the effectiveness of the proposed approach on four saliency benchmark datasets and compare it with 18 stateof-the-art saliency detection methods. Both qualitative saliency map and quantitative numerical index results indicate that our method has superior detection performance than the other counterparts under diversified scenes. Also, the proposed approach is applied to model wide synthetic aperture radar images for rapid target detection and promising results are obtained.INDEX TERMS Heuristic alternating optimization, salient object detection (SOD), SAR target detection, unsupervised learning.

show abstract

Section: Introductionmentioning

confidence: 99%

Joint Learning of Discriminative Metric Space From Multi-Context Visual Scene for Unsupervised Salient Object Detection

Wang

2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

Hybrid deep learning for object detection in drone imagery: a new metaheuristic based model

Ajith

2023

Multimed Tools Appl

View full text Add to dashboard Cite

Robust detection and refinement of saliency identification

Makram,

Salem,

El-Wakad

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Salient object detection is an increasingly popular topic in the computer vision field, particularly for images with complex backgrounds and diverse object parts. Background information is an essential factor in detecting salient objects. This paper suggests a robust and effective methodology for salient object detection. This method involves two main stages. The first stage is to produce a saliency detection map based on the dense and sparse reconstruction of image regions using a refined background dictionary. The refined background dictionary uses a boundary conductivity measurement to exclude salient object regions near the image's boundary from a background dictionary. In the second stage, the CascadePSP network is integrated to refine and correct the local boundaries of the saliency mask to highlight saliency objects more uniformly. Using six evaluation indexes, experimental outcomes conducted on three datasets show that the proposed approach performs effectively compared to the state-of-the-art methods in salient object detection, particularly in identifying the challenging salient objects located near the image's boundary. These results demonstrate the potential of the proposed framework for various computer vision applications.

show abstract

Learning Nonlinear Feature Mapping via Constrained Non-Convex Optimization for Unsupervised Salient Object Detection

Cited by 3 publications

References 47 publications

Joint Learning of Discriminative Metric Space From Multi-Context Visual Scene for Unsupervised Salient Object Detection

Joint Learning of Discriminative Metric Space From Multi-Context Visual Scene for Unsupervised Salient Object Detection

Hybrid deep learning for object detection in drone imagery: a new metaheuristic based model

Robust detection and refinement of saliency identification

Contact Info

Product

Resources

About