VAN-AD adapts a pretrained visual MAE with distribution mapping and normalizing flow modules to detect anomalies in time series data more effectively across different datasets.
Training data-efficient image transformers & distillation through attention
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
TinyUSFM distills a large ultrasound foundation model into a lightweight version using feature-gradient coreset selection and domain-separated masked image modeling, matching performance on a new 18-dataset benchmark with 6.36% of the parameters.
Perceptual quality metrics correlate strongly with each other but show minimal correlation with attack success rate across medical imaging models and datasets, making ASR alone inadequate for assessing adversarial robustness.
Benchmarking shows VAD methods transfer to autonomous driving scenes, with Tiny-Dinomaly providing the strongest accuracy-efficiency balance for edge hardware.
citing papers explorer
-
VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detection
VAN-AD adapts a pretrained visual MAE with distribution mapping and normalizing flow modules to detect anomalies in time series data more effectively across different datasets.
-
TinyUSFM: Towards Compact and Efficient Ultrasound Foundation Models
TinyUSFM distills a large ultrasound foundation model into a lightweight version using feature-gradient coreset selection and domain-separated masked image modeling, matching performance on a new 18-dataset benchmark with 6.36% of the parameters.
-
Beyond Attack Success Rate: A Multi-Metric Evaluation of Adversarial Transferability in Medical Imaging Models
Perceptual quality metrics correlate strongly with each other but show minimal correlation with attack success rate across medical imaging models and datasets, making ASR alone inadequate for assessing adversarial robustness.
-
AD4AD: Benchmarking Visual Anomaly Detection Models for Safer Autonomous Driving
Benchmarking shows VAD methods transfer to autonomous driving scenes, with Tiny-Dinomaly providing the strongest accuracy-efficiency balance for edge hardware.