Zi Huang

papers

615

total citations

papers (15)

Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling

ICCV 2023arXiv

citations

KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection

ICCV 2023arXiv

citations

CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis

ICLR 2024arXiv

citations

Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments

ECCV 2024arXiv

citations

RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation

NEURIPS 2023arXiv

citations

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

CVPR 2025arXiv

citations

SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning

ICCV 2025arXiv

citations

MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection

ICLR 2025arXiv

citations

Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation

ICCV 2025arXiv

citations

Abstract and Explore: A Novel Behavioral Metric with Cyclic Dynamics in Reinforcement Learning

AAAI 2024

citations

Object-Goal Visual Navigation via Effective Exploration of Relations Among Historical Navigation States

CVPR 2023

citations

How Far Pre-trained Models Are from Neural Collapse on the Target Dataset Informs their Transferability

ICCV 2023

citations

Zi Huang

papers (15)

Learning To Diversify for Single Domain Generalization

Semantics Disentangling for Generalized Zero-Shot Learning

Improved Feature Distillation via Projector Ensemble

Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling

KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection

CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis

Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments

RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning

MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection

Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation

Abstract and Explore: A Novel Behavioral Metric with Cyclic Dynamics in Reinforcement Learning

Object-Goal Visual Navigation via Effective Exploration of Relations Among Historical Navigation States

How Far Pre-trained Models Are from Neural Collapse on the Target Dataset Informs their Transferability

papers (15)

Learning To Diversify for Single Domain Generalization

Semantics Disentangling for Generalized Zero-Shot Learning

Improved Feature Distillation via Projector Ensemble

Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling

KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection

CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis

Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments

RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning

MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection

Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation

Abstract and Explore: A Novel Behavioral Metric with Cyclic Dynamics in Reinforcement Learning

Object-Goal Visual Navigation via Effective Exploration of Relations Among Historical Navigation States

How Far Pre-trained Models Are from Neural Collapse on the Target Dataset Informs their Transferability