no code implementations • 26 Nov 2022 • Wenbin Li, Meihao Kong, Xuesong Yang, Lei Wang, Jing Huo, Yang Gao, Jiebo Luo
In this study, we present a new unified contrastive learning representation framework (named UniCLR) suitable for all the above four kinds of methods from a novel perspective of basic affinity matrix.
no code implementations • 10 Oct 2022 • Wubing Chen, Wenbin Li, Xiao Liu, Shangdong Yang
Empirically, we evaluate MAPPG on the well-known matrix game and differential game, and verify that MAPPG can converge to the global optimum for both discrete and continuous action spaces.
1 code implementation • 10 Oct 2022 • Krish Kabra, Alexander Xiong, Wenbin Li, Minxuan Luo, William Lu, Raul Garcia, Dhananjay Vijay, Jiahui Yu, Maojie Tang, Tianjiao Yu, Hank Arnold, Anna Vallery, Richard Gibbons, Arko Barman
In this work, we present a deep learning pipeline that can be used to precisely detect, count, and monitor waterbirds using aerial imagery collected by a commercial drone.
no code implementations • 7 Oct 2022 • Wenbin Li, Zhichen Fan, Jing Huo, Yang Gao
Specifically, we propose an inter-class sKLD constraint to effectively exploit the disjoint relationship between labelled and unlabelled classes, enforcing the separability for different classes in the embedding space.
no code implementations • 22 Sep 2022 • Jack Saunders, Sajad Saeedi, Wenbin Li
Gathering data for RL is known to be a laborious task, and real-world experiments can be risky.
no code implementations • 22 Jul 2022 • Tristan Laidlow, Michael Bloesch, Wenbin Li, Stefan Leutenegger
While dense visual SLAM methods are capable of estimating dense reconstructions of the environment, they suffer from a lack of robustness in their tracking step, especially when the optimisation is poorly initialised.
1 code implementation • 14 Jul 2022 • Min Zhang, Siteng Huang, Wenbin Li, Donglin Wang
To solve this problem, we present a plug-in Hierarchical Tree Structure-aware (HTS) method, which not only learns the relationship of FSL and pretext tasks, but more importantly, can adaptively select and aggregate feature representations generated by pretext tasks to maximize the performance of FSL tasks.
no code implementations • 25 Mar 2022 • Meihao Kong, Jing Huo, Wenbin Li, Jing Wu, Yu-Kun Lai, Yang Gao
(2) Using iterative magnitude pruning, we find the matching subnetworks at 89. 2% sparsity in AdaIN and 73. 7% sparsity in SANet, which demonstrates that style transfer models can play lottery tickets too.
no code implementations • 2 Mar 2022 • Xiao Liu, Shuyang Liu, Wenbin Li, Shangdong Yang, Yang Gao
Although deep reinforcement learning has become a universal solution for complex control tasks, its real-world applicability is still limited because lacking security guarantees for policies.
no code implementations • 29 Sep 2021 • Changbin Shao, Wenbin Li, ZhenHua Feng, Jing Huo, Yang Gao
To boost the robustness of a model against adversarial examples, adversarial training has been regarded as a benchmark method.
1 code implementation • 10 Sep 2021 • Wenbin Li, Ziyi, Wang, Xuesong Yang, Chuanqi Dong, Pinzhuo Tian, Tiexin Qin, Jing Huo, Yinghuan Shi, Lei Wang, Yang Gao, Jiebo Luo
Furthermore, based on LibFewShot, we provide comprehensive evaluations on multiple benchmarks with various backbone architectures to evaluate common pitfalls and effects of different training tricks.
no code implementations • 22 Jul 2021 • Wenbin Li, Xuesong Yang, Meihao Kong, Lei Wang, Jing Huo, Yang Gao, Jiebo Luo
However, this type of methods, such as SimCLR and MoCo, relies heavily on a large number of negative pairs and thus requires either large batches or memory banks.
1 code implementation • ICCV 2021 • Zheng Gu, Wenbin Li, Jing Huo, Lei Wang, Yang Gao
Given only a few available images for a novel unseen category, few-shot image generation aims to generate more data for this category.
2 code implementations • 1 Oct 2020 • Zheng Gu, Chuanqi Dong, Jing Huo, Wenbin Li, Yang Gao
Previous caricature generation methods are obsessed with predicting definite image warping from a given photo while ignoring the intrinsic representation and distribution for exaggerations in caricatures.
no code implementations • 13 Jul 2020 • Jinglin Xu, Wenbin Li, Jiantao Shen, Xinwang Liu, Peicheng Zhou, Xiangsen Zhang, Xiwen Yao, Junwei Han
That is, we seamlessly embed various intra-view information, cross-view multi-dimension bilinear interactive information, and a new view ensemble mechanism into a unified framework to make a decision via the optimization.
1 code implementation • ICCV 2021 • Jing Huo, Shiyin Jin, Wenbin Li, Jing Wu, Yu-Kun Lai, Yinghuan Shi, Yang Gao
In this paper, we make a new assumption that image features from the same semantic region form a manifold and an image with multiple semantic regions follows a multi-manifold distribution.
no code implementations • 21 Apr 2020 • Wei Zhu, Haofu Liao, Wenbin Li, Weijian Li, Jiebo Luo
Inspired by the recent success of Few-Shot Learning (FSL) in natural image classification, we propose to apply FSL to skin disease identification to address the extreme scarcity of training sample problem.
1 code implementation • CVPR 2020 • Sinead Kearney, Wenbin Li, Martin Parsons, Kwang In Kim, Darren Cosker
We evaluate our model on both synthetic and real RGBD images and compare our results to previously published work fitting canine models to images.
1 code implementation • 13 Apr 2020 • Tiexin Qin, Wenbin Li, Yinghuan Shi, Yang Gao
Importantly, we highlight the value and importance of the distribution diversity in the augmentation-based pretext few-shot tasks, which can effectively alleviate the overfitting problem and make the few-shot model learn more robust feature representations.
Data Augmentation
Unsupervised Few-Shot Image Classification
+1
no code implementations • 1 Feb 2020 • Wenbin Li, Lei Wang, Jing Huo, Yinghuan Shi, Yang Gao, Jiebo Luo
Given the natural asymmetric relation between a query image and a support class, we argue that an asymmetric measure is more suitable for metric-based few-shot learning.
no code implementations • 18 Dec 2019 • Da Chen, Yong-Liang Yang, Zunlei Feng, Xiang Wu, Mingli Song, Wenbin Li, Yuan He, Hui Xue, Feng Mao
This strategy leads to severe meta shift issues across multiple tasks, meaning the learned prototypes or class descriptors are not stable as each task only involves their own support set.
no code implementations • 16 Nov 2019 • Wenbin Li, Lei Wang, Xingxing Zhang, Jing Huo, Yang Gao, Jiebo Luo
In this paper, instead of assuming such a distribution consistency, we propose to make this assumption at a task-level in the episodic training paradigm in order to better transfer the defense knowledge.
1 code implementation • CVPR 2019 • Wenbin Li, Lei Wang, Jinglin Xu, Jing Huo, Yang Gao, Jiebo Luo
Its key difference from the literature is the replacement of the image-level feature based measure in the final layer by a local descriptor based image-to-class measure.
no code implementations • 19 Dec 2018 • Binbin Xu, Wenbin Li, Dimos Tzoumanikas, Michael Bloesch, Andrew Davison, Stefan Leutenegger
It can provide robust camera tracking in dynamic environments and at the same time, continuously estimate geometric, semantic, and motion properties for arbitrary objects in the scene.
no code implementations • 1 Nov 2018 • Wenbin Li, Wei Xiong, Haofu Liao, Jing Huo, Yang Gao, Jiebo Luo
Furthermore, an attention mechanism is introduced to encourage our model to focus on the key facial parts so that more vivid details in these regions can be generated.
no code implementations • 3 Sep 2018 • Wenbin Li, Sajad Saeedi, John McCormac, Ronald Clark, Dimos Tzoumanikas, Qing Ye, Yuzhong Huang, Rui Tang, Stefan Leutenegger
Datasets have gained an enormous amount of popularity in the computer vision community, from training and evaluation of Deep Learning-based methods to benchmarking Simultaneous Localization and Mapping (SLAM).
1 code implementation • 15 May 2018 • Wenbin Li, Jing Huo, Yinghuan Shi, Yang Gao, Lei Wang, Jiebo Luo
Furthermore, in a progressively and nonlinearly learning way, ODML has a stronger learning ability than traditional shallow online metric learning in the case of limited available training data.
no code implementations • ICLR 2018 • Wenbin Li, Jeannette Bohg, Mario Fritz
We created a synthetic block stacking environment with physics simulation in which the agent can learn a policy end-to-end through trial and error.
no code implementations • 19 Apr 2017 • Wenbin Li, Da Chen, Zhihan Lv, Yan Yan, Darren Cosker
It is difficult to recover the motion field from a real-world footage given a mixture of camera shake and other photometric effects.
no code implementations • 9 Mar 2017 • Jing Huo, Wenbin Li, Yinghuan Shi, Yang Gao, Hujun Yin
In this paper, a new caricature dataset is built, with the objective to facilitate research in caricature recognition.
no code implementations • 29 Sep 2016 • Wenbin Li, Yang Gao, Lei Wang, Luping Zhou, Jing Huo, Yinghuan Shi
To achieve a low computational cost when performing online metric learning for large-scale data, we present a one-pass closed-form solution namely OPML in this paper.
no code implementations • 15 Sep 2016 • Wenbin Li, Aleš Leonardis, Mario Fritz
We present a learning-based approach based on simulated data that predicts stability of towers comprised of wooden blocks under different conditions and quantities related to the potential fall of the towers.
no code implementations • 7 Sep 2016 • Da Chen, Wenbin Li, Peter Hall
We propose an algorithm for dense motion estimation of smoke.
no code implementations • 31 Mar 2016 • Wenbin Li, Seyedmajid Azimi, Aleš Leonardis, Mario Fritz
In this paper, we contrast a more traditional approach of taking a model-based route with explicit 3D representations and physical simulation by an end-to-end approach that directly predicts stability and related quantities from appearance.
no code implementations • 26 Mar 2016 • Wenbin Li, Darren Cosker, Zhihan Lv, Matthew Brown
In this paper we present a dense ground truth dataset of nonrigidly deforming real-world scenes.
no code implementations • 26 Mar 2016 • Wenbin Li, Darren Cosker
Non-rigid video interpolation is a common computer vision task.
no code implementations • 7 Mar 2016 • Wenbin Li, Yang Chen, JeeHang Lee, Gang Ren, Darren Cosker
It is hard to estimate optical flow given a realworld video sequence with camera shake and other motion blur.
no code implementations • 7 Mar 2016 • Wenbin Li, Darren Cosker, Matthew Brown
We demonstrate the success of our approach by showing significant error reduction on 6 popular optical flow algorithms applied to a range of real-world nonrigid benchmarks.
no code implementations • 13 Aug 2014 • Wenbin Li, Mario Fritz
The recent progress in sparse coding and deep learning has made unsupervised feature learning methods a strong competitor to hand-crafted descriptors.
no code implementations • CVPR 2013 • Wenbin Li, Darren Cosker, Matthew Brown, Rui Tang
In this paper we present a novel non-rigid optical flow algorithm for dense image correspondence and non-rigid registration.