How would you detect anomalies in multi-modal data (image + tabular)?
hardAnswer
- (1) Fuse: (a) tabular through MLP encoder, (b) image through CNN encoder → concat embeddings → joint autoencoder or joint density model.
- (2) Score per modality then combine (max or weighted sum).
- (3) Cross-modal consistency: does the image match tabular metadata?
- (Contrastive score.) Standard in medical (image + EHR), manufacturing (sensor + camera), autonomous vehicles (camera + LiDAR).
Check yourself — multiple choice
- Only one modality
- Fuse tabular + image encoders → joint AE / density; or per-modality score + combine; or cross-modal consistency contrastive score
- Random
- Not possible
Multi-modal AD: fused encoders / per-modality combined / cross-modal consistency.
#anomaly-detection#applications
Practise Unsupervised Learning
214 interview questions in this topic.
Related questions
- Anomaly detection in time series — what changes?
- How is drift detection an unsupervised problem?
- Covariate drift vs concept drift vs label drift — the differences.
- Scan statistics — when do you use them?
- CUSUM change-point detection — how does it work?
- How do you handle 99.9% normal / 0.1% anomaly training data?