BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detection
This work addresses anomaly detection in scene graphs for applications like surveillance or robotics, representing an incremental improvement with specific gains in speed and robustness.
The paper tackles the problem of detecting anomalous relationships in scene graphs from images by proposing BUSSARD, a normalizing flow-based model that embeds object and relation tokens with a language model and uses bijective transformations for likelihood-based anomaly detection, achieving around 10% better AUROC and five times faster performance compared to the state-of-the-art on the SARD dataset.
We propose Bijective Universal Scene-Specific Anomalous Relationship Detection (BUSSARD), a normalizing flow-based model for detecting anomalous relations in scene graphs, generated from images. Our work follows a multimodal approach, embedding object and relationship tokens from scene graphs with a language model to leverage semantic knowledge from the real world. A normalizing flow model is used to learn bijective transformations that map object-relation-object triplets from scene graphs to a simple base distribution (typically Gaussian), allowing anomaly detection through likelihood estimation. We evaluate our approach on the SARD dataset containing office and dining room scenes. Our method achieves around 10% better AUROC results compared to the current state-of-the-art model, while simultaneously being five times faster. Through ablation studies, we demonstrate superior robustness and universality, particularly regarding the use of synonyms, with our model maintaining stable performance while the baseline shows 17.5% deviation. This work demonstrates the strong potential of learning-based methods for relationship anomaly detection in scene graphs. Our code is available at https://github.com/mschween/BUSSARD .