1 code implementation • CVPR 2024 • Hong Li, Yutang Feng, Song Xue, Xuhui Liu, Bohan Zeng, Shanglin Li, Boyu Liu, Jianzhuang Liu, Shumin Han, Baochang Zhang
To solve these problems we introduce an Identity-Conditioned Latent Diffusion Model for face UV-texture generation (UV-IDM) to generate photo-realistic textures based on the Basel Face Model (BFM).
no code implementations • 18 Sep 2023 • ZiMing Wang, Shumin Han, Xiaodi Wang, Jing Hao, Xianbin Cao, Baochang Zhang
Masked image modeling (MIM) methods achieve great success in various visual tasks but remain largely unexplored in knowledge distillation for heterogeneous deep models.
no code implementations • ICCV 2023 • Wenkai Dong, Song Xue, Xiaoyue Duan, Shumin Han
This technique ensures a superior trade-off between editability and high fidelity to the input image of our method.
no code implementations • 7 Apr 2023 • Jing Hao, Song Chen, Xiaodi Wang, Shumin Han
Pretraining on large-scale datasets can boost the performance of object detectors while the annotated datasets for object detection are hard to scale up due to the high labor cost.
no code implementations • 28 Nov 2022 • Xiaoyue Duan, Guoliang Kang, Runqi Wang, Shumin Han, Song Xue, Tian Wang, Baochang Zhang
Based on this observation, we propose a simple strategy, i. e., increasing the number of training shots, to mitigate the loss of intrinsic dimension caused by robustness-promoting regularization.
no code implementations • 17 Nov 2022 • Xinyu Zhang, Jiahui Chen, Junkun Yuan, Qiang Chen, Jian Wang, Xiaodi Wang, Shumin Han, Xiaokang Chen, Jimin Pi, Kun Yao, Junyu Han, Errui Ding, Jingdong Wang
That is to say, the smaller the model, the lower the mask ratio needs to be.
no code implementations • 31 Aug 2022 • Yunhao Wang, Huixin Sun, Xiaodi Wang, Bin Zhang, Chao Li, Ying Xin, Baochang Zhang, Errui Ding, Shumin Han
We develop a simple but effective module to explore the full potential of transformers for visual representation by learning fine-grained and coarse-grained features at a token level and dynamically fusing them.
6 code implementations • 7 Feb 2022 • Xiaokang Chen, Mingyu Ding, Xiaodi Wang, Ying Xin, Shentong Mo, Yunhao Wang, Shumin Han, Ping Luo, Gang Zeng, Jingdong Wang
The pretraining tasks include two tasks: masked representation prediction - predict the representations for the masked patches, and masked patch reconstruction - reconstruct the masked patches.
no code implementations • 29 Sep 2021 • Shentong Mo, Zhun Sun, Shumin Han
Recent works apply the contrastive learning on the discriminator of the Generative Adversarial Networks, and there exists little work on exploring if contrastive learning can be applied on encoders to learn disentangled representations.
no code implementations • 29 Sep 2021 • Jingwei Liu, Yi Gu, Shentong Mo, Zhun Sun, Shumin Han, Jiafeng Guo, Xueqi Cheng
In self-supervised learning frameworks, deep networks are optimized to align different views of an instance that contains the similar visual semantic information.
no code implementations • CVPR 2021 • Sheng Xu, Junhe Zhao, Jinhu Lu, Baochang Zhang, Shumin Han, David Doermann
At each layer, it exploits a differentiable binarization search (DBS) to minimize the angular error in a student-teacher framework.
no code implementations • 6 Jun 2021 • Teli Ma, Mingyuan Mao, Honghui Zheng, Peng Gao, Xiaodi Wang, Shumin Han, Errui Ding, Baochang Zhang, David Doermann
Object detection with Transformers (DETR) has achieved a competitive performance over traditional detectors, such as Faster R-CNN.
no code implementations • NeurIPS 2021 • Mingyuan Mao, Renrui Zhang, Honghui Zheng, Peng Gao, Teli Ma, Yan Peng, Errui Ding, Baochang Zhang, Shumin Han
Transformers with remarkable global representation capacities achieve competitive results for visual tasks, but fail to consider high-level local pattern information in input images.
no code implementations • 7 May 2021 • Mingyuan Mao, Baochang Zhang, David Doermann, Jie Guo, Shumin Han, Yuan Feng, Xiaodi Wang, Errui Ding
This leads to a new problem of confidence discrepancy for the detector ensembles.
1 code implementation • 28 Apr 2021 • Ying Xin, Guanzhong Wang, Mingyuan Mao, Yuan Feng, Qingqing Dang, Yanjun Ma, Errui Ding, Shumin Han
Therefore, a trade-off between effectiveness and efficiency is necessary in practical scenarios.
Ranked #1 on
Object Detection
on COCO test-dev
(Hardware Burden metric)
1 code implementation • 21 Apr 2021 • Xin Huang, Xinxin Wang, Wenyu Lv, Xiaying Bai, Xiang Long, Kaipeng Deng, Qingqing Dang, Shumin Han, Qiwen Liu, Xiaoguang Hu, dianhai yu, Yanjun Ma, Osamu Yoshie
To meet these two concerns, we comprehensively evaluate a collection of existing refinements to improve the performance of PP-YOLO while almost keep the infer time unchanged.
10 code implementations • 7 Mar 2021 • Guodong Wang, Shumin Han, Errui Ding, Di Huang
Anomaly detection is a challenging task and usually formulated as an one-class learning problem for the unexpectedness of anomalies.
Ranked #33 on
Anomaly Detection
on VisA
2 code implementations • 15 Oct 2020 • Pengcheng Yuan, Shufei Lin, Cheng Cui, Yuning Du, Ruoyu Guo, Dongliang He, Errui Ding, Shumin Han
Moreover, Hierarchical-Split block is very flexible and efficient, which provides a large space of potential network architectures for different applications.
1 code implementation • 16 Sep 2020 • Xuehui Yu, Zhenjun Han, Yuqi Gong, Nan Jiang, Jian Zhao, Qixiang Ye, Jie Chen, Yuan Feng, Bin Zhang, Xiaodi Wang, Ying Xin, Jingwei Liu, Mingyuan Mao, Sheng Xu, Baochang Zhang, Shumin Han, Cheng Gao, Wei Tang, Lizuo Jin, Mingbo Hong, Yuchao Yang, Shuiwang Li, Huan Luo, Qijun Zhao, Humphrey Shi
The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection.
5 code implementations • 23 Jul 2020 • Xiang Long, Kaipeng Deng, Guanzhong Wang, Yang Zhang, Qingqing Dang, Yuan Gao, Hui Shen, Jianguo Ren, Shumin Han, Errui Ding, Shilei Wen
We mainly try to combine various existing tricks that almost not increase the number of model parameters and FLOPs, to achieve the goal of improving the accuracy of detector as much as possible while ensuring that the speed is almost unchanged.
no code implementations • 17 Nov 2019 • Ruoyu Guo, Cheng Cui, Yuning Du, Xianglong Meng, Xiaodi Wang, Jingwei Liu, Jianfeng Zhu, Yuan Feng, Shumin Han
We present an object detection framework based on PaddlePaddle.
no code implementations • 2 Nov 2018 • Jia Li, Yafei Song, Jianfeng Zhu, Lele Cheng, Ying Su, Lin Ye, Pengcheng Yuan, Shumin Han
In this manner, the influence of bias and noise in the web data can be gradually alleviated, leading to the steadily improving performance of URNet.