Search Results for author:
Found 2 papers, 1 papers with code
Relieving Long-tailed Instance Segmentation via Pairwise Class Balance
In this paper, we explore to excavate the confusion matrix, which carries the fine-grained misclassification details, to relieve the pairwise biases, generalizing the coarse one.
Distilling Virtual Examples for Long-tailed Recognition
We tackle the long-tailed visual recognition problem from the knowledge distillation perspective by proposing a Distill the Virtual Examples (DiVE) method.
Ranked #10 on
Long-tail Learning
on iNaturalist 2018
Cannot find the paper you are looking for? You can
Submit a new open access paper.
