Zhuoxiao (Ivan) Chen

DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection
Jia Syuen Lim*, Zhuoxiao Chen*, Mahsa Baktashmotlagh, Zhi Chen, Xin Yu, Zi Huang, Yadan Luo
NeurIPS 2024
[OpenReview] [arXiv] [code]
Class-agnostic object detection (OD) can be a cornerstone or a bottleneck for many downstream vision tasks. Despite considerable advancements in bottom-up and multi-object discovery methods that leverage basic visual cues to identify salient objects, consistently achieving a high recall rate remains difficult due to the diversity of object types and their contextual complexity. In this work, we investigate using vision-language models (VLMs) to enhance object detection via a self-supervised prompt learning strategy.

DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection
Zhuoxiao Chen*, Zixin Wang*, Sen Wang, Zi Huang, Yadan Luo
MM 2024
[paper] [OpenReview] [arXiv] [code]
We propose dual-perturbation optimization (DPO) for Test-Time Adaptation for 3D Object Detection (TTA-3OD). We minimize the sharpness to cultivate a flat loss landscape to ensure model resiliency to minor data variations, thereby enhancing the generalization of the adaptation process. To fully capture the inherent variability of the test point clouds, we further introduce adversarial perturbation to the input BEV features to better simulate the noisy test environment. As the dual perturbation strategy relies on trustworthy supervision signals, we utilize a reliable Hungarian matcher to filter out pseudo-labels sensitive to perturbations. Additionally, we introduce early Hungarian cutoff to avoid error accumulation from incorrect pseudo-labels by halting the adaptation process.

In Search of Lost Online Test-Time Adaptation: A Survey
Zixin Wang, Yadan Luo, Liang Zheng, Zhuoxiao Chen, Sen Wang, Zi Huang
IJCV 2024
[paper] [arXiv] [code]
This article presents a comprehensive survey of online test-time adaptation (OTTA), focusing on effectively adapting machine learning models to distributionally different target data upon batch arrival. Despite the recent proliferation of OTTA methods, conclusions from previous studies are inconsistent due to ambiguous settings, outdated backbones, and inconsistent hyperparameter tuning, which obscure core challenges and hinder reproducibility.

Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling
Zhuoxiao Chen, Yadan Luo, Zi Huang, Zheng Wang, Mahsa Baktashmotlagh
ICCV 2023
[paper] [code] [video]
Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection. While effective, existing DA methods suffer from a substantial drop in performance when applied to a multi-class training setting, due to the co-existence of low-quality pseudo labels and class imbalance issues. In this paper, we address this challenge by proposing a novel ReDB framework tailored for learning to detect all classes at once. Our approach produces Reliable, Diverse, and class-Balanced pseudo 3D boxes to iteratively guide the self-training on a distributionally different target domain.

KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection
Yadan Luo, Zhuoxiao Chen, Zhen Fang, Zheng Zhang, Zi Huang, Mahsa Baktashmotlagh
ICCV 2023
[paper] [code]
Active learning (AL) seeks to mitigate the annotation burden through algorithms that use fewer labels and can attain performance comparable to fully supervised learning. Although AL has shown promise, current approaches prioritize the selection of unlabeled point clouds with high aleatoric and/or epistemic uncertainty, leading to the selection of more instances for labeling and reduced computational efficiency. In this paper, we resort to a novel kernel coding rate maximization (KECOR) strategy which aims to identify the most informative point clouds to acquire labels through the lens of information theory.

Exploring Active 3D Object Detection from a Generalization Perspective
Yadan Luo*, Zhuoxiao Chen*, Zijian Wang, Xin Yu, Zi Huang, Mahsa Baktashmotlagh
ICLR (Spotlight) 2023
[OpenReview] [code]
To alleviate the high annotation cost in LiDAR-based 3D object detection, active learning is a promising solution that learns to select only a small portion of unlabeled data to annotate, without compromising model performance. We jointly investigate three novel criteria in our framework CRB for point cloud acquisition - label conciseness, feature representativeness and geometric balance, which hierarchically filters out the point clouds of redundant 3D bounding box labels, latent features and geometric characteristics (e.g., point cloud density) from the unlabeled sample pool and greedily selects informative ones with fewer objects to annotate.

Source-Free Progressive Graph Learning for Open-Set Domain Adaptation
Yadan Luo, Zijian Wang, Zhuoxiao Chen, Zi Huang, Mahsa Baktashmotlagh
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
[paper] [code]
We propose a Progressive Graph Learning (PGL) framework that decomposes the target hypothesis space into the shared and unknown subspaces, and then progressively pseudo-labels the most confident known samples from the target domain for hypothesis adaptation.