Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection
Alejandro Ascarate, Leo Lebrat, Rodrigo Santa Cruz +2
Many practical anomalies are not merely rare inputs, but violations of semantic constraints: objects co-occur in structured ways, actions imply preconditions, and events satisfy te…
cs.LG2026
Testing the Test: Score-Direction Instability in Class-Split Anomaly Detection
Alejandro Ascarate, Leo Lebrat, Rodrigo Santa Cruz +2
Within-dataset class-split evaluation is widely used as a proxy for fully unconditional out-of-distribution anomaly detection. We show that this protocol can become ill-posed when…
cs.LG2026
VAE with Hyperspherical Coordinates: Improving Anomaly Detection from Hypervolume-Compressed Latent Space
Alejandro Ascarate, Leo Lebrat, Rodrigo Santa Cruz +2
Variational autoencoders (VAE) encode data into lower-dimensional latent vectors before decoding those vectors back to data. Once trained, one can hope to detect out-of-distributio…