The Community for Technology Leaders
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Honolulu, Hawaii, USA
July 21, 2017 to July 26, 2017
ISSN: 1063-6919
ISBN: 978-1-5386-0457-1
pp: 3796-3805
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 image-level 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.
convolution, image processing, inference mechanisms, learning (artificial intelligence), neural nets, object detection, prediction theory, random processes

L. Wang et al., "Learning to Detect Salient Objects with Image-Level Supervision," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, USA, 2017, pp. 3796-3805.
155 ms
(Ver 3.3 (11022016))