Winning Solutions for the Rayan AI Contest: Compositional Retrieval, Zero-Shot Anomaly Detection, and Backdoor Detection
It addresses key problems in retrieval, anomaly detection, and model security for industries like healthcare and cybersecurity, but the solutions are incremental as they build on existing contest tasks.
The paper tackled three machine learning challenges: compositional image retrieval, zero-shot anomaly detection, and backdoored model detection, achieving first-place accuracies of 95.38% and 73.14% respectively, and second place with 78% accuracy.
This report presents solutions to three machine learning challenges: compositional image retrieval, zero-shot anomaly detection, and backdoored model detection. In compositional image retrieval, we developed a system that processes visual and textual inputs to retrieve relevant images, achieving 95.38\% accuracy and ranking first with a clear margin over the second team. For zero-shot anomaly detection, we designed a model that identifies and localizes anomalies in images without prior exposure to abnormal examples, securing 1st place with 73.14\% accuracy. In the backdoored model detection task, we proposed a method to detect hidden backdoor triggers in neural networks, reaching an accuracy of 78\%, which placed our approach in second place. These results demonstrate the effectiveness of our methods in addressing key challenges related to retrieval, anomaly detection, and model security, with implications for real-world applications in industries such as healthcare, manufacturing, and cybersecurity. Code for all solutions is available online.