1 code implementation • 26 Jun 2023 • Chen Li, Xutan Peng, Teng Wang, Yixiao Ge, Mengyang Liu, Xuyuan Xu, Yexin Wang, Ying Shan
Art forms such as movies and television (TV) dramas are reflections of the real world, which have attracted much attention from the multimodal learning community recently.
no code implementations • 9 Mar 2023 • Tianyu Yu, Yangning Li, Jiaoyan Chen, Yinghui Li, Hai-Tao Zheng, Xi Chen, Qingbin Liu, Wenqiang Liu, Dongxiao Huang, Bei Wu, Yexin Wang
Inspired by this, we devise a knowledge-augmented, few-shot VRD framework leveraging both textual knowledge and visual relation knowledge to improve the generalization ability of few-shot VRD.
1 code implementation • 17 Feb 2023 • Yukang Gan, Yixiao Ge, Chang Zhou, Shupeng Su, Zhouchuan Xu, Xuyuan Xu, Quanchao Hui, Xiang Chen, Yexin Wang, Ying Shan
To tackle the challenge, we propose a binary embedding-based retrieval (BEBR) engine equipped with a recurrent binarization algorithm that enables customized bits per dimension.
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.
no code implementations • 30 Sep 2022 • Li Zhang, Yong liu, Shaoteng Liu, Tianshu Yang, Yexin Wang, Xinpeng Zhang, Hanzhou Wu
Intellectual property protection of deep neural networks is receiving attention from more and more researchers, and the latest research applies model watermarking to generative models for image processing.
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.
1 code implementation • CVPR 2022 • Yizhi Wang, Guo Pu, Wenhan Luo, Yexin Wang, Pengfei Xiong, Hongwen Kang, Zhouhui Lian
To train and evaluate our approach, we construct a dataset named as TextLogo3K, consisting of about 3, 500 text logo images and their pixel-level annotations.
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 • ICLR 2022 • Wentao Zhang, Yexin Wang, Zhenbang You, Meng Cao, Ping Huang, Jiulong Shan, Zhi Yang, Bin Cui
Graph Neural Networks (GNNs) have achieved great success in various tasks, but their performance highly relies on a large number of labeled nodes, which typically requires considerable human effort.
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.
1 code implementation • 16 Dec 2021 • Yujia Zhang, Lai-Man Po, Xuyuan Xu, Mengyang Liu, Yexin Wang, Weifeng Ou, Yuzhi Zhao, Wing-Yin Yu
Moreover, we employ a joint optimization combining pretext tasks with contrastive learning to further enhance the spatio-temporal representation learning.
1 code implementation • 4 Dec 2021 • Xinlong Sun, Yangyang Qin, Xuyuan Xu, Guoping Gong, Yang Fang, Yexin Wang
As a basic task of computer vision, image similarity retrieval is facing the challenge of large-scale data and image copy attacks.
1 code implementation • NeurIPS 2021 • Wentao Zhang, Yexin Wang, Zhenbang You, Meng Cao, Ping Huang, Jiulong Shan, Zhi Yang, Bin Cui
Message passing is the core of most graph models such as Graph Convolutional Network (GCN) and Label Propagation (LP), which usually require a large number of clean labeled data to smooth out the neighborhood over the graph.
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.
1 code implementation • 31 Jul 2021 • Wentao Zhang, Zhi Yang, Yexin Wang, Yu Shen, Yang Li, Liang Wang, Bin Cui
Data selection methods, such as active learning and core-set selection, are useful tools for improving the data efficiency of deep learning models on large-scale datasets.