Timezone: »

 
Poster
Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction
Dan Xu · Wanli Ouyang · Xavier Alameda-Pineda · Elisa Ricci · Xiaogang Wang · Nicu Sebe

Mon Dec 04 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #92 #None
in Posters Mon »

Recent works have shown that exploiting multi-scale representations deeply learned via convolutional neural networks (CNN) is of tremendous importance for accurate contour detection. This paper presents a novel approach for predicting contours which advances the state of the art in two fundamental aspects, i.e. multi-scale feature generation and fusion. Different from previous works directly considering multi-scale feature maps obtained from the inner layers of a primary CNN architecture, we introduce a hierarchical deep model which produces more rich and complementary representations. Furthermore, to refine and robustly fuse the representations learned at different scales, the novel Attention-Gated Conditional Random Fields (AG-CRFs) are proposed. The experiments ran on two publicly available datasets (BSDS500 and NYUDv2) demonstrate the effectiveness of the latent AG-CRF model and of the overall hierarchical framework.

Keywords: Computer Vision

Author Information

Dan Xu (University of Trento)
Wanli Ouyang (The Chinese University of Hong Kong)
Xavier Alameda-Pineda (INRIA)
Elisa Ricci (FBK - Technologies of Vision)
Xiaogang Wang (The Chinese University of Hong Kong)
Nicu Sebe (University of Trento)

More from the Same Authors