8 papers
SDGIC: A Semantic Disambiguation-Guided Generative Image Compression Method for Ultra-Low Bitrates
Kaile Wang, Lijun He, Haisheng Fu +2
Generative image compression has recently shown impressive perceptual quality, but often suffers from semantic inconsistency at ultra-low bitrates (bpp < 0.05), limiting its reliab…
MedSAM-CA: A CNN-Augmented ViT with Attention-Enhanced Multi-Scale Fusion for Medical Image Segmentation
Peiting Tian, Xi Chen, Haixia Bi +1
Medical image segmentation plays a crucial role in clinical diagnosis and treatment planning, where accurate boundary delineation is essential for precise lesion localization, orga…
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…