2 code implementations • 8 Apr 2024 • Jooyeon Kim, Eulrang Cho, Sehyung Kim, Hyunwoo J. Kim
Specifically, RALF consists of two modules: Retrieval Augmented Losses (RAL) and Retrieval-Augmented visual Features (RAF).
Ranked #9 on Open Vocabulary Object Detection on MSCOCO (using extra training data)
1 code implementation • ICCV 2023 • Eulrang Cho, Jooyeon Kim, Hyunwoo J. Kim
Pre-trained vision-language models (VLMs) have shown impressive performance on various downstream tasks by utilizing knowledge learned from large data.
no code implementations • CVPR 2022 • Yongkweon Jeon, Chungman Lee, Eulrang Cho, Yeonju Ro
We thus propose a new post-training non-uniform quantization method, called Mr. BiQ, allowing low bit-width quantization even on Transformer models.