Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground
arXiv:1803.06091
Abstract
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.
arXiv commentECCV 2018
References in corpus (7)
- Deeply supervised salient object detection with short connections
- STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
- DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
- Visual Saliency Based on Multiscale Deep Features
- Deep Contrast Learning for Salient Object Detection
- Enhanced-alignment Measure for Binary Foreground Map Evaluation
- Structure-measure: A New Way to Evaluate Foreground Maps
Cited by in corpus (10)
- Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network
- Advances in Deep Concealed Scene Understanding
- Light Field Salient Object Detection: A Review and Benchmark
- Boundary-Aware Segmentation Network for Mobile and Web Applications
- Joint Learning of Saliency Detection and Weakly Supervised Semantic Segmentation
- Effectiveness Assessment of Recent Large Vision-Language Models
- Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training Models
- Camouflaged Object Segmentation with Distraction Mining
- Selectivity or Invariance: Boundary-aware Salient Object Detection
- A Deeper Look at Salient Object Detection: Bi-stream Network with a Small Training Dataset