8 papers
LASA: Language-and-Source-Anchored Alignment for Domain Generalized Semantic Segmentation
Jinhong Zhu, Weiqi Yan, Shengchuan Zhang +1
Domain Generalization Semantic Segmentation (DGSS) focuses on generalizing knowledge from labeled source domains to unseen target domains where data is unavailable during the train…
Clean-Reference Streaming Detection of Lens Occlusion and Photometric Transitions for Camera Tamper Monitoring
Bo Ma, WeiQi Yan, Jinsong Wu
A surveillance camera is an image sensor whose silent physical degradation invalidates every downstream consumer of its data. In-situ integrity alarms for such vision sensors requi…
PPEDCRF: Privacy-Preserving Enhanced Dynamic CRF for Location-Privacy Protection for Sequence Videos with Minimal Detection Degradation
Bo Ma, Jinsong Wu, Weiqi Yan +2
Dashcam videos collected by autonomous or assisted-driving systems are increasingly shared for safety auditing and model improvement. Even when explicit GPS metadata are removed, a…
Bodhi VLM: Privacy-Alignment Modeling for Hierarchical Visual Representations in Vision Backbones and VLM Encoders via Bottom-Up and Top-Down Feature Search
Bo Ma, Wei Qi Yan, Jinsong Wu
Learning systems that preserve privacy often inject noise into hierarchical visual representations; a central challenge is to \emph{model} how such perturbations align with a decla…
KVSlimmer: Theoretical Insights and Practical Optimizations for Asymmetric KV Merging
Lianjun Liu, Hongli An, Weiqi Yan +4
The growing computational and memory demands of the Key-Value (KV) cache significantly limit the ability of Large Language Models (LLMs). While KV merging has emerged as a promisin…
SCOUT: Semi-supervised Camouflaged Object Detection by Utilizing Text and Adaptive Data Selection
Weiqi Yan, Lvhai Chen, Shengchuan Zhang +2
The difficulty of pixel-level annotation has significantly hindered the development of the Camouflaged Object Detection (COD) field. To save on annotation costs, previous works lev…
UCOD-DPL: Unsupervised Camouflaged Object Detection via Dynamic Pseudo-label Learning
Weiqi Yan, Lvhai Chen, Huaijia Kou +3
Unsupervised Camoflaged Object Detection (UCOD) has gained attention since it doesn't need to rely on extensive pixel-level labels. Existing UCOD methods typically generate pseudo-…
AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization
Wenlun Zhang, Yunshan Zhong, Weiqi Yan +3
The Segment Anything Model (SAM) has revolutionized image and video segmentation with its powerful zero-shot capabilities. However, its massive parameter scale and high computation…