Efficient Odd-One-Out Anomaly Detection
This work addresses efficiency challenges in anomaly detection for computer vision applications, though it is incremental as it builds on existing methods with optimizations.
The paper tackles the odd-one-out anomaly detection task, which requires identifying anomalous instances in multi-object scenes, and proposes a DINO-based model that reduces parameters by one-third and training time by threefold while maintaining competitive performance.
The recently introduced odd-one-out anomaly detection task involves identifying the odd-looking instances within a multi-object scene. This problem presents several challenges for modern deep learning models, demanding spatial reasoning across multiple views and relational reasoning to understand context and generalize across varying object categories and layouts. We argue that these challenges must be addressed with efficiency in mind. To this end, we propose a DINO-based model that reduces the number of parameters by one third and shortens training time by a factor of three compared to the current state-of-the-art, while maintaining competitive performance. Our experimental evaluation also introduces a Multimodal Large Language Model baseline, providing insights into its current limitations in structured visual reasoning tasks. The project page can be found at https://silviochito.github.io/EfficientOddOneOut/