63 citations · 77 across the 9 of their papers we have counts for
4 papers · 1 filter
Label-Occurrence-Balanced Mixup for Long-tailed Recognition
Shaoyu Zhang, Chen Chen, Xiujuan Zhang +1
Mixup is a popular data augmentation method, with many variants subsequently proposed. These methods mainly create new examples via convex combination of random data pairs and thei…
RSDet++: Point-based Modulated Loss for More Accurate Rotated Object Detection
Wen Qian, Xue Yang, Silong Peng +2
We classify the discontinuity of loss in both five-param and eight-param rotated object detection methods as rotation sensitivity error (RSE) which will result in performance degen…
Towards Fine-grained 3D Face Dense Registration: An Optimal Dividing and Diffusing Method
Zhenfeng Fan, Silong Peng, Shihong Xia
Dense vertex-to-vertex correspondence between 3D faces is a fundamental and challenging issue for 3D&2D face analysis. While the sparse landmarks have anatomically ground-truth cor…
Balanced Knowledge Distillation for Long-tailed Learning
Shaoyu Zhang, Chen Chen, Xiyuan Hu +1
Deep models trained on long-tailed datasets exhibit unsatisfactory performance on tail classes. Existing methods usually modify the classification loss to increase the learning foc…