Dan Xu, Wanli Ouyang, Xavier Alameda-Pineda, Elisa Ricci, Xiaogang Wang, and Nicu Sebe
We’ve got a paper accepted at NIPS 2017 paper on Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction [1].
Abstract: 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.
References:
- D. Xu, W. Ouyang, X. Alameda-Pineda, E. Ricci, X. Wang, and N. Sebe, “Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction,” in Advances in Neural Information Processing Systems, Long Beach, USA, 2017. [ bib pdf ]
@inproceedings{Xu-NIPS-2017, title={Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction}, author={Dan Xu and Wanli Ouyang and Xavier Alameda-Pineda and Elisa Ricci and Xiaogang Wang and Nicu Sebe}, booktitle={Advances in Neural Information Processing Systems}, year={2017}, address={Long Beach, USA}, pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Xu-NIPS-2017.pdf} }