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

TL;DR

This paper introduces a hierarchical deep model with Attention-Gated CRFs for improved multi-scale contour detection, achieving state-of-the-art results by effectively generating and fusing rich multi-scale features.

Contribution

It proposes a novel hierarchical deep architecture and Attention-Gated CRFs for better multi-scale feature fusion in contour prediction.

Findings

Effective on BSDS500 and NYUDv2 datasets

Outperforms previous contour detection methods

Demonstrates robustness and improved accuracy

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 consider- ing 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.