activity
20242026
collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2026

Deep Reprogramming Distillation for Medical Foundation Models

Siyuan Du, Yuhang Zhou, Haolin Li +5

Medical foundation models pre-trained on large-scale datasets have shown powerful versatile performance. However, when adapting medical foundation models for specific medical scena…

cs.CV2025

Learning to Instruct for Visual Instruction Tuning

Zhihan Zhou, Feng Hong, Jiaan Luo +5

We propose L2T, an advancement of visual instruction tuning (VIT). While VIT equips Multimodal LLMs (MLLMs) with promising multimodal capabilities, the current design choices for V…

cs.CV2025

Decouple before Align: Visual Disentanglement Enhances Prompt Tuning

Fei Zhang, Tianfei Zhou, Jiangchao Yao +3

Prompt tuning (PT), as an emerging resource-efficient fine-tuning paradigm, has showcased remarkable effectiveness in improving the task-specific transferability of vision-language…

cs.CV2025

Differential-informed Sample Selection Accelerates Multimodal Contrastive Learning

Zihua Zhao, Feng Hong, Mengxi Chen +5

The remarkable success of contrastive-learning-based multimodal models has been greatly driven by training on ever-larger datasets with expensive compute consumption. Sample select…

cs.CV2024

Few-Shot Anomaly Detection via Category-Agnostic Registration Learning

Chaoqin Huang, Haoyan Guan, Aofan Jiang +4

Most existing anomaly detection (AD) methods require a dedicated model for each category. Such a paradigm, despite its promising results, is computationally expensive and inefficie…

cs.CV2024

Self-supervised Anomaly Detection Pretraining Enhances Long-tail ECG Diagnosis

Aofan Jiang, Chaoqin Huang, Qing Cao +5

Current computer-aided ECG diagnostic systems struggle with the underdetection of rare but critical cardiac anomalies due to the imbalanced nature of ECG datasets. This study intro…