◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Hangzhou He

Peking University

17 papers hereh-index 5121 citations24 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author4
  • middle author13

Across the 17 of 17 papers where every author was matched, so the position is known.

fields
  • cs.CV15
  • cs.LG1
  • eess.IV1
affiliations
  • Peking University
Homepage

identity via Semantic Scholar / OpenAlex

activity
20232026
most citedScribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label

17 citations · 24 across the 16 of their papers we have counts for

collaborators
Showing 2024Show all

3 papers · 1 filter

cs.CV2024

Low-Rank Mixture-of-Experts for Continual Medical Image Segmentation

Qian Chen, Lei Zhu, Hangzhou He +4

The primary goal of continual learning (CL) task in medical image segmentation field is to solve the "catastrophic forgetting" problem, where the model totally forgets previously l…

cs.CV2024★ 17 cited

Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label

Xinliang Zhang, Lei Zhu, Hangzhou He +2

Scribble-based weakly-supervised semantic segmentation using sparse scribble supervision is gaining traction as it reduces annotation costs when compared to fully annotated alterna…

cs.LG2024

On the Duality Between Sharpness-Aware Minimization and Adversarial Training

Yihao Zhang, Hangzhou He, Jingyu Zhu +3

Adversarial Training (AT), which adversarially perturb the input samples during training, has been acknowledged as one of the most effective defenses against adversarial attacks, y…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.