Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection
This work addresses edge detection for computer vision applications, but it is incremental as it builds on existing HED and Xception methods.
The paper tackles edge detection by proposing a deep learning model that combines HED and Xception networks, resulting in thin, human-plausible edge-maps usable without retraining, and shows improvements in F-measure ODS and OIS benchmarks.
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.