H
Hanzhe Hu
Researcher at Peking University
Publications - 11
Citations - 352
Hanzhe Hu is an academic researcher from Peking University. The author has contributed to research in topics: Computer science & Graph (abstract data type). The author has an hindex of 4, co-authored 10 publications receiving 77 citations.
Papers
More filters
Proceedings ArticleDOI
Adaptive Dilated Network With Self-Correction Supervision for Counting
TL;DR: An adaptive dilated convolution and a novel supervised learning framework named self-correction (SC) supervision are proposed that achieves better performance than the state-of-the-art methods on all benchmark datasets.
Proceedings ArticleDOI
Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection
TL;DR: DCNet as mentioned in this paper proposes Dense Relation Distillation with Context-aware Aggregation (DCNet) to tackle the few-shot detection problem, which learns to adapt to novel classes with only a few annotated examples.
Posted Content
Class-wise Dynamic Graph Convolution for Semantic Segmentation.
TL;DR: A class-wise dynamic graph convolution (CDGC) module to adaptively propagate information and the Class-wise Dynamic Graph Convolution Network(CDGCNet), which consists of two main parts including the CDGC module and a basic segmentation network, forming a coarse-to-fine paradigm.
Book ChapterDOI
Class-Wise Dynamic Graph Convolution for Semantic Segmentation
TL;DR: Wang et al. as discussed by the authors proposed a class-wise dynamic graph convolution (CDGC) module to adaptively propagate information to avoid potential misleading contextual information aggregation in previous works, which achieved state-of-the-art performance on three popular semantic segmentation benchmarks including Cityscapes, PASCAL VOC 2012 and COCO Stuff.
Proceedings Article
Region-Aware Contrastive Learning for Semantic Segmentation
Hanzhe Hu,Jinshi Cui,Liwei Wang +2 more