Discovering Class-Specific Spatial Layouts for Scene Recognition

作者：Weng, Chaoqun^*; Wang, Hongxing; Yuan, Junsong; Jiang, Xudong

来源：IEEE Signal Processing Letters, 2017, 24(8): 1143-1147.

DOI：10.1109/LSP.2016.2641020

• Discovering class-specific spatial layouts
• scene recognition

Scene image is a spatial composition of objects and background contexts and finding discriminative spatial layouts is critical for scene recognition. In this letter, we propose an l(1)-regularized max-margin formulation to discover class-specific spatial layouts by jointly learning the image classifier and the class-specific spatial layouts for scene recognition. Unlike previous methods that classify images into different categories either without considering the spatial layouts explicitly or only using class-generic spatial layout, our proposed method can discover a sparse combination of class-specific spatial layouts for different scenes and boost the recognition performance. Experiments on scene-15, landuse-21, and MIT indoor-67 datasets validate the advantages of our proposed algorithm.

• 出版日期2017-8
• 单位重庆大学