REDN: A Recursive Encoder-Decoder Network for Edge Detection

In this paper, we introduce REDN: A Recursive Encoder-Decoder Network with Skip-Connections for edge detection in natural images. The proposed network is a novel integration of a Recursive Neural Network with an Encoder-Decoder architecture. The recursive network enables iterative refinement of the...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE access Jg. 8; S. 90153 - 90164
Hauptverfasser: Le, Truc, Duan, Ye
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Coders
Convolution
Datasets
Decoding
deep learning
Detectors
Edge detection
encoder-decoder network
Encoders-Decoders
Fuses
Image edge detection
Iterative methods
Machine learning
Neural networks
recursive network
Task analysis
ISSN:2169-3536, 2169-3536
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we introduce REDN: A Recursive Encoder-Decoder Network with Skip-Connections for edge detection in natural images. The proposed network is a novel integration of a Recursive Neural Network with an Encoder-Decoder architecture. The recursive network enables iterative refinement of the edges using a single network model. Adding skip-connections between encoder and decoder helps the gradients reach all the layers of a network more easily and allows information related to finer details in the early stage of the encoder to be fully utilized in the decoder. Based on our extensive experiments on popular boundary detection datasets including BSDS500 [1], NYUD [2] and Pascal Context [3], REDN significantly advances the state-of-the-art on edge detection regarding standard evaluation metrics such as Optimal Dataset Scale (ODS) F-measure, Optimal Image Scale (OIS) F-measure, and Average Precision (AP).
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2020.2994160