Zhen Zhao

Affiliations

University of Sydney

papers

574

total citations

papers (18)

Augmentation Matters: A Simple-Yet-Effective Approach to Semi-Supervised Semantic Segmentation

CVPR 2023arXiv

124

citations

Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation

CVPR 2023arXiv

citations

Adaptive Object Detection with Dual Multi-Label Prediction

ECCV 2020arXiv

citations

Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers

CVPR 2023arXiv

citations

Active Crowd Counting with Limited Supervision

ECCV 2020arXiv

citations

Instance-Specific and Model-Adaptive Supervision for Semi-Supervised Semantic Segmentation

CVPR 2023arXiv

citations

Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning

ICCV 2023arXiv

citations

Roll with the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning

AAAI 2024arXiv

citations

FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency

NEURIPS 2025arXiv

citations

Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models

ICCV 2023arXiv

citations

DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels

CVPR 2025arXiv

citations

Improving Barely Supervised Learning by Discriminating Unlabeled Samples with Super-Class

NEURIPS 2022

citations

Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling

CVPR 2023

citations

DC-SSL: Addressing Mismatched Class Distribution in Semi-Supervised Learning

CVPR 2022

citations

Zhen Zhao

Affiliations

papers (18)

Augmentation Matters: A Simple-Yet-Effective Approach to Semi-Supervised Semantic Segmentation

Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation

Adaptive Object Detection with Dual Multi-Label Prediction

Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers

Active Crowd Counting with Limited Supervision

Instance-Specific and Model-Adaptive Supervision for Semi-Supervised Semantic Segmentation

Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer

Alternate Diverse Teaching for Semi-supervised Medical Image Segmentation

Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning

Towards Semi-supervised Learning with Non-random Missing Labels

Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning

Roll with the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning

FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency

Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models

DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels

Improving Barely Supervised Learning by Discriminating Unlabeled Samples with Super-Class

Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling

DC-SSL: Addressing Mismatched Class Distribution in Semi-Supervised Learning

papers (18)

Augmentation Matters: A Simple-Yet-Effective Approach to Semi-Supervised Semantic Segmentation

Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation

Adaptive Object Detection with Dual Multi-Label Prediction

Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers

Active Crowd Counting with Limited Supervision

Instance-Specific and Model-Adaptive Supervision for Semi-Supervised Semantic Segmentation

Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer

Alternate Diverse Teaching for Semi-supervised Medical Image Segmentation

Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning

Towards Semi-supervised Learning with Non-random Missing Labels

Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning

Roll with the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning

FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency

Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models

DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels

Improving Barely Supervised Learning by Discriminating Unlabeled Samples with Super-Class

Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling

DC-SSL: Addressing Mismatched Class Distribution in Semi-Supervised Learning