Node classification is the task of predicting the labels of unlabeled no...
Contrastive learning on graphs aims at extracting distinguishable high-l...
Semi-supervised semantic segmentation (SSS) is an important task that
ut...
The long-tailed recognition (LTR) is the task of learning high-performan...
The recently proposed MaskFormer <cit.> gives a refreshed
perspective on...
Weakly supervised localization aims at finding target object regions usi...
We propose a novel 3D point cloud segmentation framework named SASO, whi...
Recently, remarkable progress has been made in weakly supervised object
...
We propose a novel fast and robust 3D point clouds segmentation framewor...
One-shot semantic segmentation poses a challenging task of recognizing t...
Weakly supervised methods usually generate localization results based on...
In this work, we propose Adversarial Complementary Learning (ACoL) to
au...
The detection of road and free space remains challenging for non-flat pl...