Search Results for author: Wenbin Li

Found 40 papers, 10 papers with code

A Unified Framework for Contrastive Learning from a Perspective of Affinity Matrix

no code implementations26 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.

Contrastive Learning Representation Learning

Learning Credit Assignment for Cooperative Reinforcement Learning

no code implementations10 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.

reinforcement-learning reinforcement Learning +2

Deep object detection for waterbird monitoring using aerial imagery

1 code implementation10 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.

Management Object Detection

Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery

no code implementations7 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.

Novel Class Discovery

Dense RGB-D-Inertial SLAM with Map Deformations

no code implementations22 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.

3D Reconstruction

Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation

1 code implementation14 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.

Few-Shot Image Classification

Playing Lottery Tickets in Style Transfer Models

no code implementations25 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.

Style Transfer

Keeping Minimal Experience to Achieve Efficient Interpretable Policy Distillation

no code implementations2 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.

Attention-based Interpretation and Response to The Trade-Off of Adversarial Training

no code implementations29 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.

LibFewShot: A Comprehensive Library for Few-shot Learning

1 code implementation10 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.

Data Augmentation Few-Shot Image Classification +1

Triplet is All You Need with Random Mappings for Unsupervised Visual Representation Learning

no code implementations22 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.

Representation Learning Self-Supervised Learning

LoFGAN: Fusing Local Representations for Few-Shot Image Generation

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.

Image Generation

CariMe: Unpaired Caricature Generation with Multiple Exaggerations

2 code implementations1 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.

Caricature Image-to-Image Translation

Embedded Deep Bilinear Interactive Information and Selective Fusion for Multi-view Learning

no code implementations13 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.

Classification General Classification +1

Manifold Alignment for Semantically Aligned Style Transfer

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.

Semantic Segmentation Style Transfer

Alleviating the Incompatibility between Cross Entropy Loss and Episode Training for Few-shot Skin Disease Classification

no code implementations21 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.

Few-Shot Learning General Classification +2

RGBD-Dog: Predicting Canine Pose from RGBD Sensors

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.

Pose Estimation Pose Prediction

Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation

1 code implementation13 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

Asymmetric Distribution Measure for Few-shot Learning

no code implementations1 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.

Few-Shot Image Classification

Semantic Regularization: Improve Few-shot Image Classification by Reducing Meta Shift

no code implementations18 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.

Few-Shot Image Classification General Classification +1

Defensive Few-shot Adversarial Learning

no code implementations16 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.

Adversarial Defense Few-Shot Learning

Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning

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.

Few-Shot Image Classification General Classification

MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM

no code implementations19 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.

Instance Segmentation Object SLAM +2

CariGAN: Caricature Generation through Weakly Paired Adversarial Learning

no code implementations1 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.


InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset

no code implementations3 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).

Simultaneous Localization and Mapping

Online Progressive Deep Metric Learning

1 code implementation15 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.

Metric Learning

Acquiring Target Stacking Skills by Goal-Parameterized Deep Reinforcement Learning

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.

reinforcement-learning reinforcement Learning

Learn to Model Motion from Blurry Footages

no code implementations19 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.

Optical Flow Estimation

WebCaricature: a benchmark for caricature recognition

no code implementations9 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.

Caricature Face Recognition

OPML: A One-Pass Closed-Form Solution for Online Metric Learning

no code implementations29 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.

Event Detection Face Verification +1

Visual Stability Prediction and Its Application to Manipulation

no code implementations15 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.

Dense Motion Estimation for Smoke

no code implementations7 Sep 2016 Da Chen, Wenbin Li, Peter Hall

We propose an algorithm for dense motion estimation of smoke.

Motion Estimation

To Fall Or Not To Fall: A Visual Approach to Physical Stability Prediction

no code implementations31 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.

Blur Robust Optical Flow using Motion Channel

no code implementations7 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.

Optical Flow Estimation

Drift Robust Non-rigid Optical Flow Enhancement for Long Sequences

no code implementations7 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.

Optical Flow Estimation

Learning Multi-Scale Representations for Material Classification

no code implementations13 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.

Classification General Classification +3

Optical Flow Estimation Using Laplacian Mesh Energy

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.

Optical Flow Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.