Zhun Zhong

Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentation

Open-Vocabulary Domain Generalization in Urban-Scene Segmentation

The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery

Organizing Unstructured Image Collections using Natural Language

Open-World Deepfake Attribution via Confidence-Aware Asymmetric Learning

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

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

SeCoV2: Semantic Connectivity-Driven Pseudo-Labeling for Robust Cross-Domain Semantic Segmentation

Cross-modality average precision optimization for visible thermal person re-identification

Democratizing Fine-grained Visual Recognition with Large Language Models

FedVQA: Personalized Federated Visual Question Answering over Heterogeneous Scenes

Multi-Domain Lifelong Visual Question Answering via Self-Critical Distillation

Dynamic Conceptional Contrastive Learning for Generalized Category Discovery

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

A Memorizing and Generalizing Framework for Lifelong Person Re-Identification

Towards Robust Person Re-Identification by Defending Against Universal Attackers

Novel Class Discovery in Semantic Segmentation

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

Class-incremental Novel Class Discovery

Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation.

Joint Representation Learning and Keypoint Detection for Cross-view Geo-localization

Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation

Source-Free Open Compound Domain Adaptation in Semantic Segmentation

Learning to Attack Real-World Models for Person Re-identification via Virtual-Guided Meta-Learning

Random Erasing Data Augmentation

Class-Aware Modality Mix and Center-Guided Metric Learning for Visible-Thermal Person Re-Identification

Learning to Adapt Invariance in Memory for Person Re-identification

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

CamStyle: A Novel Data Augmentation Method for Person Re-identification

Camera Style Adaptation for Person Re-identification

Generalizing A Person Retrieval Model Hetero- and Homogeneously

Re-ranking Person Re-identification with k-reciprocal Encoding