Scene recognition with objectness
作者：
Highlights：
• We exploit the correlations of object configurations among different scenes to choose discriminative objects and represent image descriptors with the occurrence probabilities of discriminative objects, which eliminate the negative effects caused by common objects to enhance the inter-class discriminability.
• We employ a new method patch screening to prune the patches containing non-discriminative objects by the intersection of top scored objects in patches and the discriminative objects, so that we improves the generalized characteristics of the same scenes.
• We validate the usefulness of our SDO with the state-of-the-art performance on three benchmark datasets: Scene 15, MIT Indoor 67 and SUN 397 datasets.
摘要
•We exploit the correlations of object configurations among different scenes to choose discriminative objects and represent image descriptors with the occurrence probabilities of discriminative objects, which eliminate the negative effects caused by common objects to enhance the inter-class discriminability.•We employ a new method patch screening to prune the patches containing non-discriminative objects by the intersection of top scored objects in patches and the discriminative objects, so that we improves the generalized characteristics of the same scenes.•We validate the usefulness of our SDO with the state-of-the-art performance on three benchmark datasets: Scene 15, MIT Indoor 67 and SUN 397 datasets.
论文关键词：Scene recognition,Deep learning,Co-occurrence pattern
论文评审过程：Received 22 May 2017, Revised 6 September 2017, Accepted 13 September 2017, Available online 20 September 2017, Version of Record 9 October 2017.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.09.025
