First benchmark for continual visual anomaly detection on edge devices plus Tiny-Dinomaly, a lightweight DINO-based model with 13x smaller memory, 20x lower compute, and 5-point Pixel F1 gain.
Memory efficient continual learning for edge-based visual anomaly detection.IFAC-PapersOnLine, 59(26):85–90, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Continual Visual Anomaly Detection on the Edge: Benchmark and Efficient Solutions
First benchmark for continual visual anomaly detection on edge devices plus Tiny-Dinomaly, a lightweight DINO-based model with 13x smaller memory, 20x lower compute, and 5-point Pixel F1 gain.