Search Results for author:
Found 7 papers, 2 papers with code
Zero-Shot Instance Segmentation
We follow this motivation and propose a new task set named zero-shot instance segmentation (ZSI).
Towards Understanding the Cause of Error in Few-Shot Learning
We first introduce and derive a theoretical upper bound of error rate which is constrained to 1) linear separability in the learned embedding space and 2) discrepancy of task-specific and task-independent classifier.
BiOpt: Bi-Level Optimization for Few-Shot Segmentation
On each task, the inner loop aims to learn optimized prototypes from the query images.
Prototype Refinement Network for Few-Shot Segmentation
Furthermore, to extract representative prototypes of the new classes, we use adaptation and fusion for prototype refinement.
Generalized Adaptation for Few-Shot Learning
Many Few-Shot Learning research works have two stages: pre-training base model and adapting to novel model.
Prototype Rectification for Few-Shot Learning
Few-shot learning requires to recognize novel classes with scarce labeled data.
Accurate Face Detection for High Performance
Face detection has witnessed significant progress due to the advances of deep convolutional neural networks (CNNs).
Ranked #5 on
Face Detection
on WIDER Face (Hard)
