paper-with-me

홈 › Papers

FINED: Fast Inference Network for Edge Detection

2020-12-15 · Jan Kristanto Wibisono, Hsueh-Ming Hang

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.

📄 PDF Abstract BibTeX arXiv:2012.08392

Code (1)

jannctu/FINED 공식 구현 pytorch

Tasks

Deep LearningEdge DetectionObject DetectionSemantic Segmentation

Similar Papers 제목 키워드 기반

A Fast Attention Network for Joint Intent Detection and Slot Filling on Edge Devices

2022-05-16 · Liang Huang, Senjie Liang, Feiyang Ye, Nan Gao

Intent detection and slot filling are two main tasks in natural language understanding and play an essential role in task-oriented dialogue systems. The joint learning of both tasks can improve inference accuracy and is …

Intent DetectionNatural Language Understandingslot-fillingSlot Filling+1

Five Shades of Grey for Fast and Reliable Camera Pose Estimation

2013-06-01 · CVPR 2013 6 · Adam Herout, Istvan Szentandrasi, Michal Zacharias, Marketa Dubska 외

We introduce here an improved design of the Uniform Marker Fields and an algorithm for their fast and reliable detection. Our concept of the marker field is designed so that it can be detected and recognized for camera p…

Camera Pose EstimationPose Estimation

Turning a CLIP Model into a Scene Text Spotter

2023-08-21 · Wenwen Yu, Yuliang Liu, Xingkui Zhu, Haoyu Cao 외

We exploit the potential of the large-scale Contrastive Language-Image Pretraining (CLIP) model to enhance scene text detection and spotting tasks, transforming it into a robust backbone, FastTCM-CR50. This backbone util…

object-detectionObject DetectionOriented Object DetectionPrompt Learning+2

Deep Feature Based Contextual Model for Object Detection

2016-04-14 · Wenqing Chu, Deng Cai

Object detection is one of the most active areas in computer vision, which has made significant improvement in recent years. Current state-of-the-art object detection methods mostly adhere to the framework of regions wit…

modelObjectobject-detectionObject Detection

Development of Fast Refinement Detectors on AI Edge Platforms

2019-09-24 · Min-Kook Choi, Heechul Jung

With the improvements in the object detection networks, several variations of object detection networks have been achieved impressive performance. However, the performance evaluation of most models has focused on detecti…

GPUObjectobject-detectionObject Detection