Learning To Detect Salient Objects With Image-Level Supervision
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)(2017)
摘要
Deep Neural Networks (DNNs) have substantially improved the state-of-the-art in salient object detection. However, training DNNs requires costly pixel-level annotations. In this paper, we leverage the observation that imagelevel tags provide important cues of foreground salient objects, and develop a weakly supervised learning method for saliency detection using image-level tags only. The Foreground Inference Network (FIN) is introduced for this challenging task. In the first stage of our training method, FIN is jointly trained with a fully convolutional network (FCN) for image-level tag prediction. A global smooth pooling layer is proposed, enabling FCN to assign object category tags to corresponding object regions, while FIN is capable of capturing all potential foreground regions with the predicted saliency maps. In the second stage, FIN is fine-tuned with its predicted saliency maps as ground truth. For refinement of ground truth, an iterative Conditional Random Field is developed to enforce spatial label consistency and further boost performance.Our method alleviates annotation efforts and allows the usage of existing large scale training sets with image-level tags. Our model runs at 60 FPS, outperforms unsupervised ones with a large margin, and achieves comparable or even superior performance than fully supervised counterparts.
更多查看译文
关键词
potential foreground regions,predicted saliency maps,FIN,image-level tags,image-level supervision,Deep Neural Networks,salient object detection,DNN training,pixel-level annotations,foreground inference network,iterative conditional random field,spatial label consistency,object category tags,image-level tag prediction,fully convolutional network,training method,saliency detection,weakly supervised learning method,foreground salient objects
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络