6 papers
MemOVCD: Training-Free Open-Vocabulary Change Detection via Cross-Temporal Memory Reasoning and Global-Local Adaptive Rectification
Zuzheng Kuang, Honghao Chang, Boqiang Liang +4
Open-vocabulary change detection aims to identify semantic changes in bi-temporal remote sensing images without predefined categories. Recent methods combine foundation models such…
Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration
Wei Dai, Haoyu Wang, Honghao Chang +4
Vision Language Model (VLM) typically assume complete modality input during inference. However, their effectiveness drops sharply when certain modalities are unavailable or incompl…
HeadHunt-VAD: Hunting Robust Anomaly-Sensitive Heads in MLLM for Tuning-Free Video Anomaly Detection
Zhaolin Cai, Fan Li, Ziwei Zheng +2
Video Anomaly Detection (VAD) aims to locate events that deviate from normal patterns in videos. Traditional approaches often rely on extensive labeled data and incur high computat…
What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNs
Zhihan Ren, Lijun He, Jiaxi Liang +3
Split DNNs enable edge devices by offloading intensive computation to a cloud server, but this paradigm exposes privacy vulnerabilities, as the intermediate features can be exploit…
Invisible Triggers, Visible Threats! Road-Style Adversarial Creation Attack for Visual 3D Detection in Autonomous Driving
Jian Wang, Lijun He, Yixing Yong +2
Modern autonomous driving (AD) systems leverage 3D object detection to perceive foreground objects in 3D environments for subsequent prediction and planning. Visual 3D detection ba…
Learning Fourier shapes to probe the geometric world of deep neural networks
Jian Wang, Yixing Yong, Haixia Bi +2
While both shape and texture are fundamental to visual recognition, research on deep neural networks (DNNs) has predominantly focused on the latter, leaving their geometric underst…