FINED: Fast Inference Network for Edge Detection
This work provides a more practical and efficient edge detection solution for applications constrained by computational resources, which is an incremental improvement for the computer vision community.
This paper tackles the problem of high model complexity in deep learning-based edge detection, which hinders practical usage. The authors propose FINED, a lightweight neural network that achieves state-of-the-art accuracy while significantly reducing complexity, outperforming current edge detectors at similar model sizes.
In this paper, we address the design of lightweight deep learning-based edge detection. The deep learning technology offers a significant improvement on the edge detection accuracy. However, typical neural network designs have very high model complexity, which prevents it from practical usage. In contrast, we propose a Fast Inference Network for Edge Detection (FINED), which is a lightweight neural net dedicated to edge detection. By carefully choosing proper components for edge detection purpose, we can achieve the state-of-the-art accuracy in edge detection while significantly reducing its complexity. Another key contribution in increasing the inferencing speed is introducing the training helper concept. The extra subnetworks (training helper) are employed in training but not used in inferencing. It can further reduce the model complexity and yet maintain the same level of accuracy. Our experiments show that our systems outperform all the current edge detectors at about the same model (parameter) size.