1 code implementation • 17 Apr 2024 • Qi Han, Zhibo Tian, Chengwei Xia, Kun Zhan
To address this, we employ information entropy neural estimation to utilize the potential of unlabeled samples.
1 code implementation • 28 Mar 2024 • Bu Jin, Yupeng Zheng, Pengfei Li, Weize Li, Yuhang Zheng, Sujie Hu, Xinyu Liu, Jinwei Zhu, Zhijie Yan, Haiyang Sun, Kun Zhan, Peng Jia, Xiaoxiao Long, Yilun Chen, Hao Zhao
However, the exploration of 3D dense captioning in outdoor scenes is hindered by two major challenges: 1) the \textbf{domain gap} between indoor and outdoor scenes, such as dynamics and sparse visual inputs, makes it difficult to directly adapt existing indoor methods; 2) the \textbf{lack of data} with comprehensive box-caption pair annotations specifically tailored for outdoor scenes.
no code implementations • 19 Feb 2024 • Xiaoyu Tian, Junru Gu, Bailin Li, Yicheng Liu, Chenxu Hu, Yang Wang, Kun Zhan, Peng Jia, Xianpeng Lang, Hang Zhao
We introduce DriveVLM, an autonomous driving system leveraging Vision-Language Models (VLMs) for enhanced scene understanding and planning capabilities.
no code implementations • 2 Jan 2024 • Dafeng Wei, Tian Gao, Zhengyu Jia, Changwei Cai, Chengkai Hou, Peng Jia, Fu Liu, Kun Zhan, Jingchen Fan, Yixing Zhao, Yang Wang
The demand for the retrieval of complex scene data in autonomous driving is increasing, especially as passenger vehicles have been equipped with the ability to navigate urban settings, with the imperative to address long-tail scenarios.
no code implementations • 2 Jan 2024 • Yunzhi Yan, Haotong Lin, Chenxu Zhou, Weijie Wang, Haiyang Sun, Kun Zhan, Xianpeng Lang, Xiaowei Zhou, Sida Peng
We introduce Street Gaussians, a new explicit scene representation that tackles all these limitations.
1 code implementation • 27 Jul 2023 • Yixian Ma, Kun Zhan
AttM aggregates higher-order structure and feature information to get an excellent embedding, while DiFM balances the state of each node in the graph through Laplacian diffusion learning and allows the cooperative evolution of adjacency and feature information in the graph.
1 code implementation • 26 Jul 2023 • Yixuan Ma, Xiaolin Zhang, Peng Zhang, Kun Zhan
In this paper, we theoretically illustrate that the entropy of a dataset can be approximated by maximizing the lower bound of the mutual information across different views of a graph, \ie, entropy is estimated by a neural network.
1 code implementation • 26 Jul 2023 • Zhibo Tain, Xiaolin Zhang, Peng Zhang, Kun Zhan
Semi-supervised semantic segmentation (SSS) is an important task that utilizes both labeled and unlabeled data to reduce expenses on labeling training examples.
1 code implementation • 22 Jun 2023 • Yumou Tang, Kun Zhan, Zhibo Tian, Mingxuan Zhang, Saisai Wang, Xueming Wen
Pancreas segmentation is challenging due to the small proportion and highly changeable anatomical structure.
1 code implementation • 2 Dec 2021 • Chenghua Liu, Zhuolin Liao, Yixuan Ma, Kun Zhan
Meanwhile, instead of using auto-encoder in most unsupervised learning graph neural networks, SDSNE uses a co-supervised strategy with structure information to supervise the model learning.
Ranked #1 on Multiview Clustering on Multilingual Reuters
no code implementations • 1 Jan 2021 • Chenhua Liu, Kun Zhan
We use two different branches, and inputs of the two branches are the same, which are composed of structure and feature information.
no code implementations • 1 Jan 2021 • Zhuolin Liao, Kun Zhan
The supervised loss uses the known labeled set, while a view-consistent loss is applied to the two views to obtain the consistent representation and a pseudo-label loss is designed by using the common high-confidence predictions.
1 code implementation • 2 Sep 2020 • Kun Zhan, Chaoxi Niu
We propose a new training method named as mutual teaching, i. e., we train dual models and let them teach each other during each batch.
Ranked #1 on Node Classification on CiteSeer (0.5%)
1 code implementation • 19 Jun 2019 • Changlu Chen, Chaoxi Niu, Xia Zhan, Kun Zhan
Based on the pretrained model and the constructed graph, we add a self-expressive layer to complete the generative model and then fine-tune it with a new loss function, including the reconstruction loss and a deliberately defined locality-preserving loss.
no code implementations • 22 Sep 2017 • Xuanyi Dong, Guoliang Kang, Kun Zhan, Yi Yang
For most state-of-the-art architectures, Rectified Linear Unit (ReLU) becomes a standard component accompanied with each layer.
Ranked #12 on Image Classification on SVHN