Zhun Zhong

32

Papers

179

Total Citations

Papers (32)

ReMamber: Referring Image Segmentation with Mamba Twister

Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture

Active Generalized Category Discovery

Federated Generalized Category Discovery

ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding

FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation

Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation

ChangeDiff: A Multi-Temporal Change Detection Data Generator with Flexible Text Prompts via Diffusion Model

Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery

Prior-Constrained Association Learning for Fine-Grained Generalized Category Discovery

Neighborhood Contrastive Learning for Novel Class Discovery

Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation

Novel Class Discovery in Semantic Segmentation

Dynamically Instance-Guided Adaptation: A Backward-Free Approach for Test-Time Domain Adaptive Semantic Segmentation

Sparsely Annotated Semantic Segmentation With Adaptive Gaussian Mixtures

Dynamic Conceptional Contrastive Learning for Generalized Category Discovery

A Unified Objective for Novel Class Discovery

3D-Aware Semantic-Guided Generative Model for Human Synthesis

Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation

Class-Incremental Novel Class Discovery

Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-Identification

Feature Spectrum Learning for Remote Sensing Change Detection

Pseudo-SD: Pseudo Controlled Stable Diffusion for Semi-Supervised and Cross-Domain Semantic Segmentation

Diversity-Authenticity Co-constrained Stylization for Federated Domain Generalization in Person Re-identification

Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection

Re-Ranking Person Re-Identification With k-Reciprocal Encoding

Camera Style Adaptation for Person Re-Identification

Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification

OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in an Open World

Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification

Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation

Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning