ScratchDet: Exploring to Train Single-Shot Object Detectors from Scratch
By Rui Zhu, Shifeng Zhang, Xiaobo Wang, Longyin Wen, Hailin Shi, Liefeng Bo, Tao Mei. 2018
25 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Xiaogang Wang
- Ming-Hsuan Yang
- Chen Change Loy
- Yi Yang
- Alan L. Yuille
- Chunhua Shen
Citations in the corpus
- Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection (2019, background): “Thereafter, plenty of works are presented to boost its performance in different aspects, such as fusing context information from different layers [24, 12, 69], training from scratch [50, 73], introducing new loss function [33, 6], anchor refinement and matching [66, 67], architecture redesign [21, 2”
- MMDetection: Open MMLab Detection Toolbox and Benchmark (2019, background): “• ScratchDet [40]: another exploration on training from scratch, proposed in 2018.”
- SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection (2019, background): “BN has been proved to be an effective solution of the problem through significantly smoothing the optimization landscape [49, 63].”
- Prime Sample Attention in Object Detection (2019, unknown): “Other variants include [26, 12, 27, 28].”
- Recent Advances in Deep Learning for Object Detection (2019, background): “There are some works [107,160,161] exploring training object 1357 detectors from scratch.”
- Object Detection in 20 Years: A Survey (2019, background): “To speed up training and improve stability, some researchers introduce dense connection and batch normalization to accelerate the back-propagation in shallow layers [238, 284].”
- VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results (2019, methodology): “To keep the favourable performance independent to the network architecture, Zhu et al. [50] train detectors from scratch using BatchNorm with larger learning rate.”