no code implementations • 22 Jun 2023 • Binjie Zhang, Yixiao Ge, Xuyuan Xu, Ying Shan, Mike Zheng Shou
In situations involving system upgrades that require updating the upstream foundation model, it becomes essential to re-train all downstream modules to adapt to the new foundation model, which is inflexible and inefficient.
no code implementations • 13 Oct 2022 • Binjie Zhang, Shupeng Su, Yixiao Ge, Xuyuan Xu, Yexin Wang, Chun Yuan, Mike Zheng Shou, Ying Shan
The traditional model upgrading paradigm for retrieval requires recomputing all gallery embeddings before deploying the new model (dubbed as "backfilling"), which is quite expensive and time-consuming considering billions of instances in industrial applications.
1 code implementation • 29 Apr 2022 • Shupeng Su, Binjie Zhang, Yixiao Ge, Xuyuan Xu, Yexin Wang, Chun Yuan, Ying Shan
The task of privacy-preserving model upgrades in image retrieval desires to reap the benefits of rapidly evolving new models without accessing the raw gallery images.
2 code implementations • 15 Mar 2022 • Guanyu Cai, Yixiao Ge, Binjie Zhang, Alex Jinpeng Wang, Rui Yan, Xudong Lin, Ying Shan, Lianghua He, XiaoHu Qie, Jianping Wu, Mike Zheng Shou
Recent dominant methods for video-language pre-training (VLP) learn transferable representations from the raw pixels in an end-to-end manner to achieve advanced performance on downstream video-language retrieval.
2 code implementations • 3 Mar 2022 • Binjie Zhang, Yixiao Ge, Yantao Shen, Shupeng Su, Fanzi Wu, Chun Yuan, Xuyuan Xu, Yexin Wang, Ying Shan
The task of backward-compatible representation learning is therefore introduced to support backfill-free model upgrades, where the new query features are interoperable with the old gallery features.
1 code implementation • 24 Jan 2022 • Binjie Zhang, Yixiao Ge, Yantao Shen, Yu Li, Chun Yuan, Xuyuan Xu, Yexin Wang, Ying Shan
In contrast, hot-refresh model upgrades deploy the new model immediately and then gradually improve the retrieval accuracy by backfilling the gallery on-the-fly.
no code implementations • ICLR 2022 • Binjie Zhang, Yixiao Ge, Yantao Shen, Yu Li, Chun Yuan, Xuyuan Xu, Yexin Wang, Ying Shan
In contrast, hot-refresh model upgrades deploy the new model immediately and then gradually improve the retrieval accuracy by backfilling the gallery on-the-fly.
no code implementations • 23 Sep 2020 • Binjie Zhang, Yu Li, Chun Yuan, Dejing Xu, Pin Jiang, Ying Shan
The task of language-guided video temporal grounding is to localize the particular video clip corresponding to a query sentence in an untrimmed video.