Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction

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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [45 references]  Display  Hide  Download

https://hal.inria.fr/hal-01646112
Contributor : Xavier Alameda-Pineda <>
Submitted on : Thursday, November 23, 2017 - 11:43:59 AM
Last modification on : Thursday, February 7, 2019 - 3:47:13 PM

File

Xu-NIPS-2017.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01646112, version 1

Collections

Citation

Dan Xu, Wanli Ouyang, Xavier Alameda-Pineda, Elisa Ricci, Xiaogang Wang, et al.. Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction. Advances in Neural Information Processing Systems, Dec 2017, Long Beach, United States. pp.3961-3970. ⟨hal-01646112⟩

Share

Metrics

Record views

224

Files downloads

96