5 papers
SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity
Ke Ma, Jiaqi Tang, Bin Guo +8
Despite the growing integration of deep models into mobile terminals, the accuracy of these models declines significantly due to various deployment interferences. Test-time adaptat…
Hawk: Learning to Understand Open-World Video Anomalies
Jiaqi Tang, Hao Lu, Ruizheng Wu +7
Video Anomaly Detection (VAD) systems can autonomously monitor and identify disturbances, reducing the need for manual labor and associated costs. However, current VAD systems are…
GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors
LI Yang, WU Ruizheng, LI Jiyong +1
Learning surfaces from neural radiance field (NeRF) became a rising topic in Multi-View Stereo (MVS). Recent Signed Distance Function (SDF)-based methods demonstrated their ability…
Learning to Remove Wrinkled Transparent Film with Polarized Prior
Jiaqi Tang, Ruizheng Wu, Xiaogang Xu +2
In this paper, we study a new problem, Film Removal (FR), which attempts to remove the interference of wrinkled transparent films and reconstruct the original information under fil…
An Incremental Unified Framework for Small Defect Inspection
Jiaqi Tang, Hao Lu, Xiaogang Xu +7
Artificial Intelligence (AI)-driven defect inspection is pivotal in industrial manufacturing. Yet, many methods, tailored to specific pipelines, grapple with diverse product portfo…