Rethinking Continual Anomaly Detection on the Edge: Benchmarking Under Realistic Industrial Conditions

AIPR assessment

Problem difficulty is high. Continual anomaly detection for industrial inspection is a competitive and increasingly crowded area, and the paper is trying to address both benchmarking and deployability, not just a narrow model variant. The strengths reinforce each other well: a new drift benchmark, head-to-head comparison, and edge profiling all support the central claim that simple replay plus strong features may outperform specialized CAD machinery. The weaknesses also compound: no code release

Abstract

Continual anomaly detection (CAD) addresses the need for industrial inspection systems to adapt to evolving production conditions, yet existing methods share three critical gaps: unrealistic evaluation, no systematic comparison, and no consideration of edge deployment constraints. We introduce a unified benchmark combining discrete-task evaluation on structural and logical anomalies, a novel continuous drift protocol, the first head-to-head comparison of all published CAD methods, and computational efficiency profiling on edge hardware. Our results reveal that existing CAD methods do not consistently outperform traditional approaches with simple experience replay. Thus motivated, we propose DINOSaur, a training-free method combining a frozen DINOv3 backbone with spatially-indexed coreset memory and neighborhood-restricted anomaly scoring. DINOSaur achieves zero forgetting by construction, outperforms all evaluated methods across all five protocols, and runs at sub-100\,ms inference on an NVIDIA Jetson Orin Nano, with on-device adaptation to new tasks in under 30 seconds.

Score Breakdown

More from this week

• Optimus: Elastic Decoding for Efficient Diffusion LLM Serving
• TubiFM: Unified Item, Carousel, and Search Ranking for Streaming Discovery
• Context Features Are Cheap: Rank-Aware Decomposition for Efficient Feature Interaction in Recommender Systems
• Learning High-Frequency Continuous Action Chunks in Latent Space
• A Pragmatic Approach to Learned Indexing in RocksDB: Targeted Optimizations with Minimal System Modification

More in Computer Vision

• RealDocBench: A Benchmark for Field-Level QA and Layout Understanding on Real-World Regulated Documents
• Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends
• FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing
• Beyond Visual Fidelity: Benchmarking Super-Resolution Models for Large-Scale Remote Sensing Imagery via Downstream Task Integration
• Railway Artificial Intelligence Learning Benchmark (RAIL-BENCH): A Benchmark Suite for Perception in the Railway Domain