1 code implementation • 28 Jan 2024 • Shaofeng Zhang, Jinfa Huang, Qiang Zhou, Zhibin Wang, Fan Wang, Jiebo Luo, Junchi Yan
At inference, we generate images with arbitrary expansion multiples by inputting an anchor image and its corresponding positional embeddings.
1 code implementation • 14 Nov 2023 • Jinpei Guo, Shaofeng Zhang, Runzhong Wang, Chang Liu, Junchi Yan
Meanwhile, on Pascal VOC, QueryTrans improves the accuracy of NGMv2 from $80. 1\%$ to $\mathbf{83. 3\%}$, and BBGM from $79. 0\%$ to $\mathbf{84. 5\%}$.
Ranked #1 on Graph Matching on PASCAL VOC (matching accuracy metric)
1 code implementation • NeurIPS 2023 • Junkun Yuan, Xinyu Zhang, Hao Zhou, Jian Wang, Zhongwei Qiu, Zhiyin Shao, Shaofeng Zhang, Sifan Long, Kun Kuang, Kun Yao, Junyu Han, Errui Ding, Lanfen Lin, Fei Wu, Jingdong Wang
To further capture human characteristics, we propose a structure-invariant alignment loss that enforces different masked views, guided by the human part prior, to be closely aligned for the same image.
no code implementations • 10 Oct 2023 • Ning Liao, Shaofeng Zhang, Renqiu Xia, Min Cao, Yu Qiao, Junchi Yan
Instead of evaluating the models directly, in this paper, we try to evaluate the Vision-Language Instruction-Tuning (VLIT) datasets.
1 code implementation • 3 Aug 2023 • Qiang Zhou, Chaohui Yu, Shaofeng Zhang, Sitong Wu, Zhibing Wang, Fan Wang
To this end, we propose to extract features corresponding to regional objects as soft prompts for LLM, which provides a straightforward and scalable approach and eliminates the need for LLM fine-tuning.
no code implementations • 23 Jun 2023 • Shaofeng Zhang, Feng Zhu, Rui Zhao, Junchi Yan
On classification tasks, for ViT-S, ADCLR achieves 77. 5% top-1 accuracy on ImageNet with linear probing, outperforming our baseline (DINO) without our devised techniques as plug-in, by 0. 5%.
no code implementations • 8 Dec 2022 • Hengrui Zhang, Qitian Wu, Yu Wang, Shaofeng Zhang, Junchi Yan, Philip S. Yu
Contrastive learning methods based on InfoNCE loss are popular in node representation learning tasks on graph-structured data.
no code implementations • 28 Apr 2022 • Shaofeng Zhang, Feng Zhu, Junchi Yan, Rui Zhao, Xiaokang Yang
Scalability is an important consideration for deep graph neural networks.
no code implementations • CVPR 2022 • Shaofeng Zhang, Lyn Qiu, Feng Zhu, Junchi Yan, Hengrui Zhang, Rui Zhao, Hongyang Li, Xiaokang Yang
Existing symmetric contrastive learning methods suffer from collapses (complete and dimensional) or quadratic complexity of objectives.
no code implementations • ICLR 2022 • Shaofeng Zhang, Feng Zhu, Junchi Yan, Rui Zhao, Xiaokang Yang
The proposed two methods (FCL, ICL) can be combined synthetically, called Zero-CL, where ``Zero'' means negative samples are \textbf{zero} relevant, which allows Zero-CL to completely discard negative pairs i. e., with \textbf{zero} negative samples.
no code implementations • 29 Sep 2021 • Hengrui Zhang, Qitian Wu, Shaofeng Zhang, Junchi Yan, David Wipf, Philip S. Yu
In this paper, we propose ESCo (Effective and Scalable Contrastive), a new contrastive framework which is essentially an instantiation of the Information Bottleneck principle under self-supervised learning settings.
no code implementations • 29 Sep 2021 • Shaofeng Zhang, Meng Liu, Junchi Yan, Hengrui Zhang, Lingxiao Huang, Pinyan Lu, Xiaokang Yang
Negative pairs are essential in contrastive learning, which plays the role of avoiding degenerate solutions.
no code implementations • 1 Jan 2021 • Shaofeng Zhang, Junchi Yan, Xiaokang Yang
Despite their success in perception over the last decade, deep neural networks are also known ravenous to labeled data for training, which limits their applicability to real-world problems.
no code implementations • NeurIPS 2020 • Shaofeng Zhang, Meng Liu, Junchi Yan
Ensemble is a general way of improving the accuracy and stability of learning models, especially for the generalization ability on small datasets.