Have We Solved Edge Detection? A Review of State-of-the-Art Datasets and DNN Based Techniques
Recent Deep Neural Networks (DNNs) based edge detection methods claim to beat human performance on small scale datasets like BSDS500. But is the problem of edge detection really solved? To answer this question, we review the existing dataset limitations as well as the generalization capabilities of...
Main Authors: | Muhammad Mubashar, Naeemullah Khan, Abdur Rehman Sajid, Muhammad Hashim Javed, Naveed Ul Hassan |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9812621/ |
Similar Items
-
Edge Computing-Assisted DNN Image Recognition System With Progressive Image Retransmission
by: Mutsuki Nakahara, et al.
Published: (2022-01-01) -
Optimum Selection of DNN Model and Framework for Edge Inference
by: Delia Velasco-Montero, et al.
Published: (2018-01-01) -
DNN Partitioning for Inference Throughput Acceleration at the Edge
by: Thomas Feltin, et al.
Published: (2023-01-01) -
RUnT: A Network Combining Residual U-Net and Transformer for Vertebral Edge Feature Fusion Constrained Spine CT Image Segmentation
by: Hao Xu, et al.
Published: (2023-01-01) -
Edge-cloud cooperation for DNN inference via reinforcement learning and supervised learning
by: Zhang, Tinghao, et al.
Published: (2024)