no code implementations • 7 Apr 2024 • Yuanfeng Xu, Yuhao Chen, Zhongzhan Huang, Zijian He, Guangrun Wang, Philip Torr, Liang Lin
In this paper, we present AnimateZoo, a zero-shot diffusion-based video generator to address this challenging cross-species animation issue, aiming to accurately produce animal animations while preserving the background.
no code implementations • 13 Mar 2024 • Jing Wu, Jia-Wang Bian, Xinghui Li, Guangrun Wang, Ian Reid, Philip Torr, Victor Adrian Prisacariu
We propose GaussCtrl, a text-driven method to edit a 3D scene reconstructed by the 3D Gaussian Splatting (3DGS).
1 code implementation • 2 Mar 2024 • Linsheng Chen, Guangrun Wang, Liuchun Yuan, Keze Wang, Ken Deng, Philip H. S. Torr
Furthermore, the cascading learning of NeRF-VPT introduces adaptability to scenarios with sparse inputs, resulting in a significant enhancement of accuracy for sparse-view novel view synthesis.
1 code implementation • 2 Mar 2024 • Guangrun Wang, Changlin Li, Liuchun Yuan, Jiefeng Peng, Xiaoyu Xian, Xiaodan Liang, Xiaojun Chang, Liang Lin
Addressing this problem, we modularize a large search space into blocks with small search spaces and develop a family of models with the distilling neural architecture (DNA) techniques.
1 code implementation • 27 Feb 2024 • Tao Tang, Guangrun Wang, Yixing Lao, Peng Chen, Jie Liu, Liang Lin, Kaicheng Yu, Xiaodan Liang
Through extensive experiments across various datasets and scenes, we demonstrate the effectiveness of our approach in facilitating better interaction between LiDAR and camera modalities within a unified neural field.
no code implementations • 31 Jan 2024 • Qijia Shen, Guangrun Wang
To overcome these limitations, we propose a method for reconstructing 3D geometry from the diverse and unstructured Imagenet dataset without camera pose information.
1 code implementation • ICCV 2023 • Guangyi Chen, Xiao Liu, Guangrun Wang, Kun Zhang, Philip H. S. Torr, Xiao-Ping Zhang, Yansong Tang
To bridge these gaps, in this paper, we propose Tem-Adapter, which enables the learning of temporal dynamics and complex semantics by a visual Temporal Aligner and a textual Semantic Aligner.
Ranked #1 on Video Question Answering on SUTD-TrafficQA
no code implementations • ICCV 2023 • BinBin Yang, Yi Luo, Ziliang Chen, Guangrun Wang, Xiaodan Liang, Liang Lin
Thanks to the rapid development of diffusion models, unprecedented progress has been witnessed in image synthesis.
no code implementations • ICCV 2023 • Kaixin Cai, Pengzhen Ren, Yi Zhu, Hang Xu, Jianzhuang Liu, Changlin Li, Guangrun Wang, Xiaodan Liang
To address this issue, we propose MixReorg, a novel and straightforward pre-training paradigm for semantic segmentation that enhances a model's ability to reorganize patches mixed across images, exploring both local visual relevance and global semantic coherence.
1 code implementation • 7 Jul 2023 • Xiao Liu, Guangyi Chen, Yansong Tang, Guangrun Wang, Xiao-Ping Zhang, Ser-Nam Lim
Composing simple elements into complex concepts is crucial yet challenging, especially for 3D action generation.
1 code implementation • 20 Apr 2023 • Tang Tao, Longfei Gao, Guangrun Wang, Yixing Lao, Peng Chen, Hengshuang Zhao, Dayang Hao, Xiaodan Liang, Mathieu Salzmann, Kaicheng Yu
We address this challenge by formulating, to the best of our knowledge, the first differentiable end-to-end LiDAR rendering framework, LiDAR-NeRF, leveraging a neural radiance field (NeRF) to facilitate the joint learning of geometry and the attributes of 3D points.
1 code implementation • 31 Jan 2023 • Pengzhen Ren, Changlin Li, Hang Xu, Yi Zhu, Guangrun Wang, Jianzhuang Liu, Xiaojun Chang, Xiaodan Liang
Specifically, we first propose text-to-views consistency modeling to learn correspondence for multiple views of the same input image.
no code implementations • 27 Nov 2022 • Guangrun Wang, Philip H. S. Torr
Proving that classifiers have learned the data distribution and are ready for image generation has far-reaching implications, for classifiers are much easier to train than generative models like DDPMs and GANs.
no code implementations • 12 Nov 2022 • Xipeng Chen, Guangrun Wang, Dizhong Zhu, Xiaodan Liang, Philip H. S. Torr, Liang Lin
In this paper, we propose a novel Neural Sewing Machine (NSM), a learning-based framework for structure-preserving 3D garment modeling, which is capable of learning representations for garments with diverse shapes and topologies and is successfully applied to 3D garment reconstruction and controllable manipulation.
1 code implementation • 16 Oct 2022 • Tao Tang, Changlin Li, Guangrun Wang, Kaicheng Yu, Xiaojun Chang, Xiaodan Liang
Despite the success, its development and application on self-supervised vision transformers have been hindered by several barriers, including the high search cost, the lack of supervision, and the unsuitable search space.
no code implementations • 8 Aug 2022 • Guangcong Wang, Guangrun Wang, Wenqi Liang, JianHuang Lai
We extend the traditional hypothesis-testing method to a hypothesis-training-testing statistical inference method to validate the hypothesis on the weight similarity of neural networks.
1 code implementation • CVPR 2022 • Changlin Li, Bohan Zhuang, Guangrun Wang, Xiaodan Liang, Xiaojun Chang, Yi Yang
First, we develop a strong manual baseline for progressive learning of ViTs, by introducing momentum growth (MoGrow) to bridge the gap brought by model growth.
1 code implementation • CVPR 2022 • Pengzhen Ren, Changlin Li, Guangrun Wang, Yun Xiao, Qing Du, Xiaodan Liang, Xiaojun Chang
Recently, a surge of interest in visual transformers is to reduce the computational cost by limiting the calculation of self-attention to a local window.
1 code implementation • CVPR 2022 • Guangrun Wang, Yansong Tang, Liang Lin, Philip H.S. Torr
Inspired by perceptual learning that could use cross-view learning to perceive concepts and semantics, we propose a novel AE that could learn semantic-aware representation via cross-view image reconstruction.
1 code implementation • 21 Sep 2021 • Changlin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, Xiaojun Chang
Dynamic networks have shown their promising capability in reducing theoretical computation complexity by adapting their architectures to the input during inference.
1 code implementation • Findings (EMNLP) 2021 • Chenhe Dong, Guangrun Wang, Hang Xu, Jiefeng Peng, Xiaozhe Ren, Xiaodan Liang
In this paper, we have a critical insight that improving the feed-forward network (FFN) in BERT has a higher gain than improving the multi-head attention (MHA) since the computational cost of FFN is 2$\sim$3 times larger than MHA.
1 code implementation • ICCV 2021 • Jiefeng Peng, Jiqi Zhang, Changlin Li, Guangrun Wang, Xiaodan Liang, Liang Lin
We attribute this ranking correlation problem to the supernet training consistency shift, including feature shift and parameter shift.
1 code implementation • ICCV 2021 • Guangrun Wang, Keze Wang, Guangcong Wang, Philip H. S. Torr, Liang Lin
In this paper, we reveal two contradictory phenomena in contrastive learning that we call under-clustering and over-clustering problems, which are major obstacles to learning efficiency.
Ranked #1 on Self-Supervised Person Re-Identification on SYSU-30k
no code implementations • 31 Mar 2021 • Guangrun Wang, Liang Lin, Rongcong Chen, Guangcong Wang, Jiqi Zhang
In this work, we prove that dynamically adapting network architectures tailored for each domain task along with weight finetuning benefits in both efficiency and effectiveness, compared to the existing image recognition pipeline that only tunes the weights regardless of the architecture.
1 code implementation • CVPR 2021 • Changlin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, Xiaojun Chang
Here, we explore a dynamic network slimming regime, named Dynamic Slimmable Network (DS-Net), which aims to achieve good hardware-efficiency via dynamically adjusting filter numbers of networks at test time with respect to different inputs, while keeping filters stored statically and contiguously in hardware to prevent the extra burden.
1 code implementation • ICCV 2021 • Changlin Li, Tao Tang, Guangrun Wang, Jiefeng Peng, Bing Wang, Xiaodan Liang, Xiaojun Chang
In this work, we present Block-wisely Self-supervised Neural Architecture Search (BossNAS), an unsupervised NAS method that addresses the problem of inaccurate architecture rating caused by large weight-sharing space and biased supervision in previous methods.
no code implementations • 1 Jan 2021 • Guangcong Wang, JianHuang Lai, Wenqi Liang, Guangrun Wang
Specifically, we select the longest chain from the source model and transfer it to the longest chain of the target model.
1 code implementation • ECCV 2020 • Bailin Li, Bowen Wu, Jiang Su, Guangrun Wang, Liang Lin
Many algorithms try to predict model performance of the pruned sub-nets by introducing various evaluation methods.
Ranked #6 on Network Pruning on ImageNet
1 code implementation • CVPR 2020 • Hongjun Wang, Guangrun Wang, Ya Li, Dongyu Zhang, Liang Lin
To examine the robustness of ReID systems is rather important because the insecurity of ReID systems may cause severe losses, e. g., the criminals may use the adversarial perturbations to cheat the CCTV systems.
1 code implementation • 29 Nov 2019 • Changlin Li, Jiefeng Peng, Liuchun Yuan, Guangrun Wang, Xiaodan Liang, Liang Lin, Xiaojun Chang
Moreover, we find that the knowledge of a network model lies not only in the network parameters but also in the network architecture.
Ranked #1 on Neural Architecture Search on CIFAR-100
no code implementations • 25 Sep 2019 • Guangcong Wang, JianHuang Lai, Guangrun Wang, Wenqi Liang
We present a Function Feature Learning (FFL) method that can measure the similarity of non-convex neural networks.
no code implementations • 27 Jul 2019 • Guangcong Wang, Jian-Huang Lai, Wenqi Liang, Guangrun Wang
Most of the existing approaches focus on specific visual tasks while ignoring the relations between them.
1 code implementation • 8 Apr 2019 • Guangrun Wang, Guangcong Wang, Xujie Zhang, Jian-Huang Lai, Zhengtao Yu, Liang Lin
Learning a Re-ID model with bag-level annotation is called the weakly supervised Re-ID problem.
Ranked #2 on Person Re-Identification on SYSU-30k
1 code implementation • CVPR 2019 • Guangrun Wang, Keze Wang, Liang Lin
This paper presents a novel adaptively connected neural network (ACNet) to improve the traditional convolutional neural networks (CNNs) {in} two aspects.
Ranked #1 on Document Classification on Cora
no code implementations • NeurIPS 2018 • Guangrun Wang, Jiefeng Peng, Ping Luo, Xinjiang Wang, Liang Lin
In this paper, we present a novel normalization method, called Kalman Normalization (KN), for improving and accelerating the training of DNNs, particularly under the context of micro-batches.
no code implementations • 9 Feb 2018 • Guangrun Wang, Jiefeng Peng, Ping Luo, Xinjiang Wang, Liang Lin
As an indispensable component, Batch Normalization (BN) has successfully improved the training of deep neural networks (DNNs) with mini-batches, by normalizing the distribution of the internal representation for each hidden layer.
no code implementations • ICCV 2017 • Ping Luo, Guangrun Wang, Liang Lin, Xiaogang Wang
The estimated labelmaps that capture accurate object classes and boundaries are used as ground truths in training to boost performance.
no code implementations • 27 Sep 2017 • Ruimao Zhang, Liang Lin, Guangrun Wang, Meng Wang, WangMeng Zuo
Rather than relying on elaborative annotations (e. g., manually labeled semantic maps and relations), we train our deep model in a weakly-supervised learning manner by leveraging the descriptive sentences of the training images.
no code implementations • CVPR 2017 • Guangrun Wang, Ping Luo, Liang Lin, Xiaogang Wang
This work significantly increases segmentation accuracy of CNNs by learning from an Image Descriptions in the Wild (IDW) dataset.
no code implementations • 13 May 2016 • Liang Lin, Guangrun Wang, WangMeng Zuo, Xiangchu Feng, Lei Zhang
Cross-domain visual data matching is one of the fundamental problems in many real-world vision tasks, e. g., matching persons across ID photos and surveillance videos.
no code implementations • 15 Apr 2016 • Guangrun Wang, Liang Lin, Shengyong Ding, Ya Li, Qing Wang
The past decade has witnessed the rapid development of feature representation learning and distance metric learning, whereas the two steps are often discussed separately.
Ranked #7 on Person Re-Identification on SYSU-30k (using extra training data)
no code implementations • CVPR 2016 • Liang Lin, Guangrun Wang, Rui Zhang, Ruimao Zhang, Xiaodan Liang, WangMeng Zuo
This paper addresses a fundamental problem of scene understanding: How to parse the scene image into a structured configuration (i. e., a semantic object hierarchy with object interaction relations) that finely accords with human perception.
no code implementations • 11 Dec 2015 • Shengyong Ding, Liang Lin, Guangrun Wang, Hongyang Chao
Identifying the same individual across different scenes is an important yet difficult task in intelligent video surveillance.
Ranked #9 on Person Re-Identification on SYSU-30k (using extra training data)