Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search.
Peidong LiuGengwei ZhangBochao WangHang XuXiaodan LiangYong JiangZhenguo LiPublished in: CoRR (2021)
Keyphrases
- loss function
- object detection
- pairwise
- support vector
- solution path
- learning to rank
- logistic regression
- risk minimization
- boosting framework
- empirical risk
- reproducing kernel hilbert space
- data mining
- regularization term
- convergence speed
- hinge loss
- binary classification
- object class
- similarity measure
- computer vision