Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground

By Deng-Ping Fan, Jiangjiang Liu, Shanghua Gao, Qibin Hou, Ali Borji, Ming-Ming Cheng. European Conference on Computer Vision, 2018

333 citations recorded by the source corpus.

We provide a comprehensive evaluation of salient object detection (SOD) models. Our analysis identifies a serious design bias of existing SOD datasets which assumes that each image contains at least one clearly outstanding salient object in low clutter. The design bias has led to a saturated high performance for state-of-the-art SOD models when evaluated on existing datasets. The models, however, still perform far from being satisfactory when applied to real-world daily scenes. Based on our analyses, we first identify 7 crucial aspects that a comprehensive and balanced dataset should fulfill. Then, we propose a new high quality dataset and update the previous saliency benchmark. Specifically, our SOC (Salient Objects in Clutter) dataset, includes images with salient and non-salient objects from daily object categories. Beyond object category annotations, each salient image is accompanied by attributes that reflect common challenges in real-world scenes. Finally, we report attribute-based performance assessment on our dataset.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e6c5acdeb034d627962204986056ac04060214e9

How researchers see this paper

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

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

Citations in the corpus

BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (2020, background): “, cluttered backgrounds [16], low-intensity environments, and varying illuminations) [4, 49].”
Shifting More Attention to Video Salient Object Detection (2019, background): “Salient object detection (SOD) targets at extracting the most attention-grabbing objects from still images [17] or dynamic videos.”
Uncertainty-aware Joint Salient Object and Camouflaged Object Detection (2021, methodology): “Table 2 shows that we achieve 5/6 best performance, except on SOC testing dataset [8].”
Stacked Cross Refinement Network for Edge-Aware Salient Object Detection (2019, methodology): “In the challenging SOC dataset [8], each salient image is accompanied by attributes that reﬂect common challenges in real-world scenes.”
UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders (2020, neutral): “, VSOD [19], RGB SOD [13, 65], Co-SOD [17]).”
Concealed Object Detection (2021, methodology): “We adopt the strategy described in [12] to analyze this bias.”
Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks (2019, methodology): “Following [83], the images are carefully selected to cover diverse challenging cases (e.”
Label Decoupling Framework for Salient Object Detection (2020, methodology): “In particularly, we demonstrate the good performance of LDF in different challenging scenes in the SOC dataset [8].”
Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection (2021, background): “To solve the ambiguities caused by indistinguishable textures, unlike generic / salient object detection models [9,16,31,32,35,43,59,61], current COD approaches usually distill extra features from the shared context (e.”
Kaleido-BERT: Vision-Language Pre-training on Fashion Domain (2021, background): “, BAS [56], EGNet [81], ICON [84] or other SOTAs in the recent paper [17]) to obtain the foreground mask and then lock (e.”
Efficient and Accurate Arbitrary-Shaped Text Detection With Pixel Aggregation Network (2019, background): “In virtue of recent development of object detection [41, 30, 11, 9, 5, 8, 56] and segmentation [1, 55, 33, 53, 6, 7] based on CNN [15, 20, 47, 25], scene text detection has witnessed great progress [46, 42, 57, 31, 35, 49, 24].”
ADBench: Anomaly Detection Benchmark (2022, methodology): “We consider saliency detection (SD) [44, 46] and camouﬂage detection (CD) [45] as good inspirations and applications of AD tasks.”
High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling (2020, methodology): “We collect 82,020 object masks from densely annotated segmentation datasets, including video segmentation [11], semantic segmentation [14], salient object segmentation [23,31,15], and human parsing [24].”
Improving Convolutional Networks With Self-Calibrated Convolutions (2020, background): “, ImageNet [30]) are usually adopted as backbones to extract strong representative features for down-stream tasks, such as object detection [23, 29, 2, 8], segmentation [45, 11], and human keypoint detection [11, 39].”
Saliency Detection via a Multiple Self-Weighted Graph-Based Manifold Ranking (2020, background): “The goal of saliency detection is to obtain the most compelling regions from images [2], [3] or videos [4].”
EGNet: Edge Guidance Network for Salient Object Detection (2019, neutral): “More details are introduced in [1,2,9].”
Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection (2019, background): “Although many works [10, 14, 22, 30, 44, 45, 47] have devoted to RGB saliency detection and have achieved appealing performance, they might fail when coping with complex scenarios, such as multiple or transparent objects, similar foreground and background, complex background and low-intensity enviro”