Recent advances on loss functions in deep learning for computer vision
Neurocomputing(2022)
摘要
•The properties and comparisons about each loss function are presented.•Two guidelines on designing or selecting the loss functions are proposed.•The application scenarios about each loss function are summarized.•The SOTA results of each task and the losses used in SOTA are summarized.•Some frontier challenges are also discussed in our review.
更多查看译文
关键词
Loss function,Deep learning,Object detection,Face recognition,Image segmentation
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要