Search Results for author:
Found 3 papers, 2 papers with code
Reconciling Object-Level and Global-Level Objectives for Long-Tail Detection
Specifically, complementary to the object-level classification loss for model discrimination, we design a generalized average precision (GAP) loss to explicitly optimize the global-level score ranking across different objects.
Label-Occurrence-Balanced Mixup for Long-tailed Recognition
When applying mixup to long-tailed data, a label suppression issue arises, where the frequency of label occurrence for each class is imbalanced and most of the new examples will be completely or partially assigned with head labels.
Balanced Knowledge Distillation for Long-tailed Learning
Existing methods usually modify the classification loss to increase the learning focus on tail classes, which unexpectedly sacrifice the performance on head classes.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
