collaborators

7 papers

cs.CV2026

Topology-Driven Transferability Estimation for 3D Medical Vision Foundation Models

Jiaqi Tang, Shaoyang Zhang, Fandong Zhang +3

The growing number of medical vision foundation models highlights the need for effective model selection. However, mainstream selection methods rely on exhaustive fine-tuning, whic…

cs.CV2026

Topology-Driven Transferability Estimation of Medical Foundation Models for Segmentation

Jiaqi Tang, Shaoyang Zhang, Xiaoqi Wang +3

The advent of large-scale self-supervised learning (SSL) has produced a vast zoo of medical foundation models. However, selecting optimal medical foundation models for specific seg…

cs.CV2026

The Texture-Shape Dilemma: Boundary-Safe Synthetic Generation for 3D Medical Transformers

Jiaqi Tang, Weixuan Xu, Shu Zhang +2

Vision Transformers (ViTs) have revolutionized medical image analysis, yet their data-hungry nature clashes with the scarcity and privacy constraints of clinical archives. Formula-…

cs.CV2026

Fake It Right: Injecting Anatomical Logic into Synthetic Supervised Pre-training for Medical Segmentation

Jiaqi Tang, Mengyan Zheng, Shu Zhang +2

Vision Transformers (ViTs) excel in 3D medical segmentation but require massive annotated datasets. While Self-Supervised Learning (SSL) mitigates this using unlabeled data, it sti…

cs.LG2025

Shaping Initial State Prevents Modality Competition in Multi-modal Fusion: A Two-stage Scheduling Framework via Fast Partial Information Decomposition

Jiaqi Tang, Yinsong Xu, Yang Liu +1

Multi-modal fusion often suffers from modality competition during joint training, where one modality dominates the learning process, leaving others under-optimized. Overlooking the…

cs.HC2025

Advancing Radar Hand Gesture Recognition: A Hybrid Spectrum Synthetic Framework Merging Simulation with Neural Networks

Jiaqi Tang, Xinbo Xu, Yinsong Xu +1

Millimeter wave (mmWave) radar sensors play a vital role in hand gesture recognition (HGR) by detecting subtle motions while preserving user privacy. However, the limited scale of…