Hi, I'm Byungsoo 👋 🎃
I'm a researcher and developer 🐛 🐛 🐛
🏢 I'm currently working at NAVER & LINE corp.
Connect with me:
📑 Latest Research
📜 Large-scale Bilingual Language-Image Contrastive Learning in ICLRW2022,
github📜 Self-Distilled Hashing for Deep Image Retrieval in arxiv2021📜 Towards Light-weight and Real-time Line Segment Detection in AAAI2022, github📜 Learning with Memory-based Virtual Classes for Deep Metric Learning in ICCV2021 github📜 RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Network in arxiv2021📜 Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning in AAAI2021, github📜 Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning in CVPR2020, github📜 Symmetrical Synthesis for Deep Metric Learning in AAAI2020, github📜 An Effective Pipeline for a Real-world Clothes Retrieval System in CVFAD workshop on CVPR2020📜 A Benchmark on Tricks for Large-scale Image Retrieval in arxiv2019📜 Combination of Multiple Global Descriptors for Image Retrieval in arxiv2019, github
💻 Latest Project
- DALL-E reproduction: Working on reproducing OpenAI's DALL-E and sharing pre-trained models
- Computer vision leaderboard: Leaderboards of famous benchmarks in computer vision
- Filter Response Norm in MXNet: MXNet implementation of FRN published in CVPR2020
- Get daily arxiv noti: Get daily arxiv notification filtered by keywords of your interests