IEEE Transactions on Image Processing · 2019 · 20 citations · 87 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionActive LearningFeature DetectionImage AnnotationImage LabelingObject DetectionScene UnderstandingBenchmark DatasetsPool-based Active LearningSaliency DetectionSalient Object DetectionSalient Region DetectionUncertainty SamplingVisual SaliencyVisual Saliency Detection
Saliency detection task has witnessed a booming interest for years, due to the growth of the computer vision community. In this paper, we introduce a new saliency model that performs active learning with kernelized subspace ranker (KSR) referred to as KSR-AL. This pool-based active learning algorithm ranks the informativeness of unlabeled data by considering both uncertainty sampling and information density, thereby minimizing the cost of labeling. The informative images are selected to train the KSR iteratively and incrementally. The learning model of this algorithm is designed on object-level proposals and region-based convolutional neural network (R-CNN) features, by jointly learning a Rank-SVM classifier and a subspace projection. When the active learning process meets its stopping criteria, the saliency map of each image is generated by a weight fusion of its top-ranked proposals, whose ranking scores are graded by the learned ranker. We show that the KSR-AL achieves a reduction in annotation, as well as improvement in performance, compared with the supervised learning scheme. Besides, the proposed algorithm also outperforms the state-of-the-art methods. These improvements are demonstrated by extensive experiments on six publicly available benchmark datasets.
87
A density-based algorithm for discovering clusters in large spatial Databases with Noise
Martin Ester, Hans‐Peter Kriegel, Jörg Sander et al. · 1996 · 19.1K citations
Saliency Detection: A Spectral Residual Approach
Xiaodi Hou, Liqing Zhang · 2007 · 3.4K citations
Global contrast based salient region detection
Ming‐Ming Cheng, Guoxin Zhang, Niloy J. Mitra et al. · 2011 · 3.1K citations