harimkang / anomalib

An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.

👋 Hi all, I'm Harim, AI R&D Engineer working at

💡 Current Interests

• Computer Vision, Semi-SL, Multi-Modal, Generative Model
• A new application using an existing model or task
• DevOps/MLOps
• Various ideas (Multiple projects that benefit the common good)

💜 About Me

AI R&D Engineer at Intel (2021.6~)

• [Research] Semi-SL for multi-class classification
• [Research] Class-Incremental Learning for Detection & Instance Segmentation
• [Dev] Developer of Model-Preparation-Algorithm
• [Dev] Developer of OpenVINO Training Extension (OTX)
  • Responsible for the Semi-SL Classification algorithm - Link
  • OTX v1.0 CLI (Overall Design & Implementation)
  • OTX v2.0 API/CLI Design
• [Dev] Contribution
  • Geti
  • Geti-sdk
  • Anomalib

SW Engineer (Contract workers dispatched to Intel) (2020.5~)

• [Dev] Microservices (API) Integration & E2E test validation of Intel Product: QA Validation
• [Dev] Contributor of Datumaro
  • Implement a sampler that performs sampling to consider the balance of the class

🌀 Languages

📬 Contacts