Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection

4 Sep 2019  ·  Xavier Soria, Edgar Riba, Angel D. Sappa ·

This paper proposes a Deep Learning based edge detector, which is inspired on both HED (Holistically-Nested Edge Detection) and Xception networks. The proposed approach generates thin edge-maps that are plausible for human eyes; it can be used in any edge detection task without previous training or fine tuning process. As a second contribution, a large dataset with carefully annotated edges has been generated. This dataset has been used for training the proposed approach as well the state-of-the-art algorithms for comparisons. Quantitative and qualitative evaluations have been performed on different benchmarks showing improvements with the proposed method when F-measure of ODS and OIS are considered.

PDF Abstract

Datasets


Introduced in the Paper:

BIPED

Used in the Paper:

BSD BSDS500 CID

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Edge Detection CID DexiNed (WACV'2020) ODS 0.65 # 1

Methods