Designing effective power law-based loss function for faster and better bounding box regression
- 27 May 2021
- journal article
- research article
- Published by Springer Nature in Machine Vision and Applications
- Vol. 32 (4) , 1-10
Abstract
No abstract availableKeywords
This publication has 25 references indexed in Scilit:
- Focal Loss for Dense Object Detection2017
- Mask R-CNN2017
- UnitBox2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- A Two-Phase Algorithm Based on Kurtosis Curvelet Energy and Unsupervised Spectral Regression for Segmentation of SAR ImagesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- A New Statistical-Based Kurtosis Wavelet Energy Feature for Texture Recognition of SAR ImagesIEEE Transactions on Geoscience and Remote Sensing, 2012
- Segmentation as selective search for object recognition2011
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009