Salient object detection: A survey

By Ali Borji, Ming-Ming Cheng, Huaizu Jiang, Jia Li. Computational Visual Media, 2014

836 citations recorded by the source corpus.

Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision. While many models have been proposed and several applications have emerged, a deep understanding of achievements and issues remains lacking. We aim to provide a comprehensive review of recent progress in salient object detection and situate this field among other closely related areas such as generic scene segmentation, object proposal generation, and saliency for fixation prediction. Covering 228 publications, we survey i) roots, key concepts, and tasks, ii) core techniques and main modeling trends, and iii) datasets and evaluation metrics for salient object detection. We also discuss open problems such as evaluation metrics and dataset bias in model performance, and suggest future research directions.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f6bbd62f7b5a33d10a6ca8935db76c58f6256d25

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

Citations in the corpus

Artificial intelligence in the creative industries: a review (2020, background): “The purpose of SOD differs from fixation detection, which predicts where humans look, but there is a strong correlation between the two (Borji et al. 2019).”
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything (2023, background): “Salient object segmentation [4] aims to segment the most visually attractive objects from an image.”
Structure-Measure: A New Way to Evaluate Foreground Maps (2017, background): “…crucial in evaluating and comparing various computer vision algorithm for applications such as object detection [6, 8, 24, 40], saliency prediction [5, 20, 42], image segmentation [41], content-based image retrieval [12, 15, 22], semantic segmentation [21,45,46] and image collection browsing…”
Stacked Cross Refinement Network for Edge-Aware Salient Object Detection (2019, methodology): “More details of them can be found in [2, 3].”
Deep Learning for Generic Object Detection: A Survey (2018, background): “15 Salient Object Detection: A Survey [19] 2014 arXiv A survey for salient object detection”
Interactive Image Segmentation With First Click Attention (2020, background): “…deep learning techniques, the demand for mask-level annotations has increased dramatically in some ﬁelds, such as salient object detection [4, 9, 14, 23], semantic segmentation [34], instance segmentation [21, 35], camouﬂaged object detection [15], and image/video manipulation [17, 28,…”
Res2Net: A New Multi-Scale Backbone Architecture (2019, methodology): “gnition tasks, including image classiﬁcation [28], object detection [43], attention prediction [45], target tracking [63], action recognition [46], semantic segmentation [6], salient object detection [2], [24], object proposal [12], [43], skeleton extraction [67], stereo matching [42], and edge dete”
Non-local Deep Features for Salient Object Detection (2017, background): “[5] for more details on unsupervised meth-ods.”
Understanding Deep Learning Techniques for Image Segmentation (2019, background): “While some of them specialized in application areas [107, 123, 185], while other focused on specific types of algorithms [20, 19, 59].”
Salient Object Detection in the Deep Learning Era: An In-Depth Survey (2019, background): “More recently, the review is extended in [43] that covers both traditional non-deep methods and recent deep ones, and discusses the relation w.r.t. several other closely-related research areas such as special-purpose object detection, ﬁxation prediction and segmentation.”
Fast Segment Anything (2023, background): “The aim of salient object segmentation [5] is to segment the most attention-grabbing objects from an image.”
Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation (2020, background): “Moreover, the color and texture of objects in indoor scenes are not always representative [15].”
Camouflaged Object Detection (2020, background): “…intrinsic similarities between the target object and the background make COD far more challenging than the traditional salient object detection [1,5,17,25,62– 66, In addition to its scientiﬁc value, COD is also beneﬁcial for applications in the ﬁelds of computer vision (for search-and-rescue…”
JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection (2020, background): “Salient object detection (SOD) aims at detecting the objects in a scene that humans would naturally focus on [2, 9, 78].”
Learning to Detect Salient Objects with Image-Level Supervision (2017, methodology): “Therefore, the object detection data set is more suitable for solving saliency co-occurrence problem [3].”