Publications

Critical Sampling for Data-Driven Modeling of Unknown Dynamical Systems

When a robot is exploring an unknown dynamical system, we often face the following important question:what is the minimum number of …

Ce Zhang, Siqi Wu, Zhihai He, Zhao Joy Sun

Learning to Adapt CLIP for Few-Shot Monocular Depth Estimation

Pre-trained Vision-Language Models (VLMs), such as CLIP, have shown enhanced performance across a range of tasks that involve the …

Xueting Hu, Ce Zhang, Yi Zhang, Bowen Hai, Ke Yu, Zhihai He

Cross-inferential networks for source-free unsupervised domain adaptation

One central challenge in source-free unsupervised domain adaptation (UDA) is the lack of an effective approach to evaluate the …

Yushun Tang, Qinghai Guo, Zhihai He

BDC-Adapter Brownian Distance Covariance for Better Vision-Language Reasoning

Large-scale pre-trained Vision-Language Models (VLMs), such as CLIP and ALIGN, have introduced a new paradigm for learning transferable …

Yi Zhang, Ce Zhang, Zihan Liao, Yushun Tang, Zhihai He

Unsupervised Prototype Adapter for Vision-Language Models

Recently, large-scale pre-trained vision-language models (e.g. CLIP and ALIGN) have demonstrated remarkable effectiveness in acquiring …

Yi Zhang, Ce Zhang, Xueting Hu, Zhihai He

Cycle optimization metric learning for few-shot classification

Metric learning methods are widely used in few-shot learning due to their simplicity and effectiveness. Most existing methods directly …

Qifan Liu, Wenming Cao, Zhihai He

Critical Sampling for Robust Evolution Operator Learning of Unknown Dynamical Systems

Given an unknown dynamical system, what is the minimum number of samples needed for effective learning of its governing laws and …

Ce Zhang, Kailiang Wu, Zhihai He

Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation

A central challenge in human pose estimation, as well as in many other machine learning and prediction tasks, is the generalization …

Zhehan Kan, Shuoshuo Chen, Ce Zhang, Yushun Tang, Zhihai He

Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation

Fully test-time adaptation aims to adapt the network model based on sequential analysis of input samples during the inference stage to …

Yushun Tang, Ce Zhang, Heng Xu, Shuoshuo Chen, Jie Cheng, Luziwei Leng, Qinghai Guo, Zhihai He

Self-guided information for few-shot classification

Few-shot classification aims to identify novel categories using only a few labeled samples. Generally, the metric-based few-shot …

Zhineng Zhao, Qifan Liu, Wenming Cao, Deliang Lian, Zhihai He

Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation

We observe that human poses exhibit strong group-wise structural correlation and spatial coupling between keypoints due to the …

Zhehan Kan, Shuoshuo Chen, Zeng Li, Zhihai He