Search Results for author:
Found 4 papers, 3 papers with code
Boundary and Relation Distillation for Semantic Segmentation
Concurrently, the relation distillation transfers implicit relations from the teacher model to the student model using pixel-level self-relation as a bridge, ensuring that the student's mask has strong target region connectivity.
On Non-Random Missing Labels in Semi-Supervised Learning
Our method is three-fold: 1) We propose Class-Aware Propensity (CAP) that exploits the unlabeled data to train an improved classifier using the biased labeled data.
Distilling Causal Effect of Data in Class-Incremental Learning
We propose a causal framework to explain the catastrophic forgetting in Class-Incremental Learning (CIL) and then derive a novel distillation method that is orthogonal to the existing anti-forgetting techniques, such as data replay and feature/label distillation.
Learning to Segment the Tail
Real-world visual recognition requires handling the extreme sample imbalance in large-scale long-tailed data.
