4 papers
AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM
Sunghyun Ahn, Youngwan Jo, Kijung Lee +3
Video anomaly detection (VAD) is crucial for video analysis and surveillance in computer vision. However, existing VAD models rely on learned normal patterns, which makes them diff…
GranQ: Efficient Channel-wise Quantization via Vectorized Pre-Scaling for Zero-Shot QAT
Inpyo Hong, Youngwan Jo, Hyojeong Lee +3
Zero-shot quantization (ZSQ) enables neural network compression without original training data, making it a promising solution for restricted data access scenarios. To compensate f…
Advanced Knowledge Transfer: Refined Feature Distillation for Zero-Shot Quantization in Edge Computing
Inpyo Hong, Youngwan Jo, Hyojeong Lee +2
We introduce AKT (Advanced Knowledge Transfer), a novel method to enhance the training ability of low-bit quantized (Q) models in the field of zero-shot quantization (ZSQ). Existin…
VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detection
Sunghyun Ahn, Youngwan Jo, Kijung Lee +1
Video anomaly detection (VAD) is a crucial task in video analysis and surveillance within computer vision. Currently, VAD is gaining attention with memory techniques that store the…