Explainable Deep Convolutional Multi-Type Anomaly Detection

TL;DR

This paper introduces MultiTypeFCDD, a lightweight, explainable convolutional model that detects and differentiates multiple anomaly types across object categories using only image-level labels, suitable for resource-constrained environments.

Contribution

The paper presents MultiTypeFCDD, a novel unified framework for explainable multi-type anomaly detection that eliminates the need for multiple models and is computationally efficient.

Findings

Achieves 96.4% I-AUROC on Real-IAD dataset.

Uses only 1% of the size of large Vision-Language Models.

Effectively differentiates anomaly types across categories.

Abstract

Explainable anomaly detection methods often have the capability to identify and spatially localise anomalies within an image but lack the capability to differentiate the type of anomaly. Furthermore, they often require the costly training and maintenance of separate models for each object category. The lack of specificity is a significant research gap because identifying the type of anomaly (e.g., "Crack" vs. "Scratch") is crucial for accurate diagnosis that facilitates cost-saving operational decisions across diverse application domains. While some recent large-scale Vision-Language Models (VLMs) have begun to address this, they are computationally intensive and memory-heavy, restricting their use in real-time or embedded systems. We propose MultiTypeFCDD, a simple and lightweight convolutional framework designed as a practical alternative for explainable multi-type anomaly detection. MultiTypeFCDD uses only image-level labels to learn and produce multi-channel heatmaps, where each channel is trained to correspond to a specific anomaly type. The model functions as a single, unified framework capable of differentiating anomaly types across multiple object categories, eliminating the need to train and manage separate models for each object category. We evaluated our proposed method on the Real-IAD dataset and it delivers competitive results (96.4% I-AUROC) at just over 1% the size of state-of-the-art VLM models used for similar tasks. This makes it a highly practical and viable solution for real-world applications where computational resources are tightly constrained.