Search Results for author:
Found 2 papers, 1 papers with code
A dual-branch model with inter- and intra-branch contrastive loss for long-tailed recognition
Therefore, in this paper, we propose a simple yet effective model, named Dual-Branch Long-Tailed Recognition (DB-LTR), which includes an imbalanced learning branch and a Contrastive Learning Branch (CoLB).
MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation
Existing few-shot segmentation methods are based on the meta-learning strategy and extract instance knowledge from a support set and then apply the knowledge to segment target objects in a query set.
Ranked #11 on
Few-Shot Semantic Segmentation
on COCO-20i (1-shot)
Cannot find the paper you are looking for? You can
Submit a new open access paper.
