Search Results for author: Wenyu Liu

Found 102 papers, 65 papers with code

MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction

1 code implementation10 Aug 2023 Bencheng Liao, Shaoyu Chen, Yunchi Zhang, Bo Jiang, Qian Zhang, Wenyu Liu, Chang Huang, Xinggang Wang

We propose a unified permutation-equivalent modeling approach, \ie, modeling map element as a point set with a group of equivalent permutations, which accurately describes the shape of map element and stabilizes the learning process.

Autonomous Driving

Symphonize 3D Semantic Scene Completion with Contextual Instance Queries

1 code implementation27 Jun 2023 Haoyi Jiang, Tianheng Cheng, Naiyu Gao, Haoyang Zhang, Wenyu Liu, Xinggang Wang

By incorporating the queries as the instance feature representations within the scene, Symphonies dynamically encodes the instance-centric semantics to interact with the image and volume features while avoiding the dense voxel-wise modeling.

3D Semantic Scene Completion from a single RGB image Autonomous Driving

SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth

1 code implementation8 Jun 2023 Zelin Liu, Xinggang Wang, Cheng Wang, Wenyu Liu, Xiang Bai

By integrating the pseudo-depth method and the DCM strategy into the data association process, we propose a new tracker, called SparseTrack.

 Ranked #1 on Multi-Object Tracking on MOT20 (using extra training data)

Depth Estimation Multi-Object Tracking +1

Matte Anything: Interactive Natural Image Matting with Segment Anything Models

1 code implementation7 Jun 2023 Jingfeng Yao, Xinggang Wang, Lang Ye, Wenyu Liu

We leverage task-specific vision models to enhance the performance of natural image matting.

Image Matting

GaitGS: Temporal Feature Learning in Granularity and Span Dimension for Gait Recognition

no code implementations31 May 2023 Haijun Xiong, Yunze Deng, Xiaohu Huang, Xinggang Wang, Wenyu Liu, Bin Feng

In order to fully harness the potential of gait recognition, it is crucial to consider temporal features at various granularities and spans.

Gait Recognition

LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation

1 code implementation CVPR 2023 Song Wang, Wentong Li, Wenyu Liu, Xiaolu Liu, Jianke Zhu

To mitigate the defects caused by lacking semantic cues in LiDAR data, we present an online Camera-to-LiDAR distillation scheme to facilitate the semantic learning from image to point cloud.

Autonomous Driving

VMA: Divide-and-Conquer Vectorized Map Annotation System for Large-Scale Driving Scene

2 code implementations19 Apr 2023 Shaoyu Chen, Yunchi Zhang, Bencheng Liao, Jiafeng Xie, Tianheng Cheng, Wei Sui, Qian Zhang, Chang Huang, Wenyu Liu, Xinggang Wang

We design a divide-and-conquer annotation scheme to solve the spatial extensibility problem of HD map generation, and abstract map elements with a variety of geometric patterns as unified point sequence representation, which can be extended to most map elements in the driving scene.

Autonomous Driving

TinyDet: Accurate Small Object Detection in Lightweight Generic Detectors

no code implementations7 Apr 2023 Shaoyu Chen, Tianheng Cheng, Jiemin Fang, Qian Zhang, Yuan Li, Wenyu Liu, Xinggang Wang

Small object detection requires the detection head to scan a large number of positions on image feature maps, which is extremely hard for computation- and energy-efficient lightweight generic detectors.

object-detection Small Object Detection

WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation

1 code implementation3 Apr 2023 Lianghui Zhu, Yingyue Li, Jiemin Fang, Yan Liu, Hao Xin, Wenyu Liu, Xinggang Wang

Thus a novel weight-based method is proposed to end-to-end estimate the importance of attention heads, while the self-attention maps are adaptively fused for high-quality CAM results that tend to have more complete objects.

Weakly-supervised Learning Weakly supervised Semantic Segmentation +1

RPTQ: Reorder-based Post-training Quantization for Large Language Models

1 code implementation3 Apr 2023 Zhihang Yuan, Lin Niu, Jiawei Liu, Wenyu Liu, Xinggang Wang, Yuzhang Shang, Guangyu Sun, Qiang Wu, Jiaxiang Wu, Bingzhe Wu

In this paper, we identify that the challenge in quantizing activations in LLMs arises from varying ranges across channels, rather than solely the presence of outliers.


MobileInst: Video Instance Segmentation on the Mobile

no code implementations30 Mar 2023 Renhong Zhang, Tianheng Cheng, Shusheng Yang, Haoyi Jiang, Shuai Zhang, Jiancheng Lyu, Xin Li, Xiaowen Ying, Dashan Gao, Wenyu Liu, Xinggang Wang

To address those issues, we present MobileInst, a lightweight and mobile-friendly framework for video instance segmentation on mobile devices.

Instance Segmentation Semantic Segmentation +1

OpenInst: A Simple Query-Based Method for Open-World Instance Segmentation

no code implementations28 Mar 2023 Cheng Wang, Guoli Wang, Qian Zhang, Peng Guo, Wenyu Liu, Xinggang Wang

Fortunately, we have identified two observations that help us achieve the best of both worlds: 1) query-based methods demonstrate superiority over dense proposal-based methods in open-world instance segmentation, and 2) learning localization cues is sufficient for open world instance segmentation.

Autonomous Driving Instance Segmentation +1

Generalizable Neural Voxels for Fast Human Radiance Fields

no code implementations27 Mar 2023 Taoran Yi, Jiemin Fang, Xinggang Wang, Wenyu Liu

Rendering moving human bodies at free viewpoints only from a monocular video is quite a challenging problem.

Novel View Synthesis

Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance

no code implementations23 Mar 2023 Zhihang Yuan, Jiawei Liu, Jiaxiang Wu, Dawei Yang, Qiang Wu, Guangyu Sun, Wenyu Liu, Xinggang Wang, Bingzhe Wu

Post-training quantization (PTQ) is a popular method for compressing deep neural networks (DNNs) without modifying their original architecture or training procedures.

Benchmarking Data Augmentation +1

VAD: Vectorized Scene Representation for Efficient Autonomous Driving

2 code implementations21 Mar 2023 Bo Jiang, Shaoyu Chen, Qing Xu, Bencheng Liao, Jiajie Chen, Helong Zhou, Qian Zhang, Wenyu Liu, Chang Huang, Xinggang Wang

In this paper, we propose VAD, an end-to-end vectorized paradigm for autonomous driving, which models the driving scene as a fully vectorized representation.

Autonomous Driving Trajectory Planning

Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction

1 code implementation15 Mar 2023 Bencheng Liao, Shaoyu Chen, Bo Jiang, Tianheng Cheng, Qian Zhang, Wenyu Liu, Chang Huang, Xinggang Wang

We present a path-based online lane graph construction method, termed LaneGAP, which end-to-end learns the path and recovers the lane graph via a Path2Graph algorithm.

Autonomous Driving graph construction +1

Understanding Self-Supervised Pretraining with Part-Aware Representation Learning

no code implementations27 Jan 2023 Jie Zhu, Jiyang Qi, Mingyu Ding, Xiaokang Chen, Ping Luo, Xinggang Wang, Wenyu Liu, Leye Wang, Jingdong Wang

The study is mainly motivated by that random views, used in contrastive learning, and random masked (visible) patches, used in masked image modeling, are often about object parts.

Contrastive Learning Representation Learning

Graph Contrastive Learning for Skeleton-based Action Recognition

1 code implementation26 Jan 2023 Xiaohu Huang, Hao Zhou, Jian Wang, Haocheng Feng, Junyu Han, Errui Ding, Jingdong Wang, Xinggang Wang, Wenyu Liu, Bin Feng

In this paper, we propose a graph contrastive learning framework for skeleton-based action recognition (\textit{SkeletonGCL}) to explore the \textit{global} context across all sequences.

Action Recognition Contrastive Learning +2

A Simple Adaptive Unfolding Network for Hyperspectral Image Reconstruction

1 code implementation24 Jan 2023 Junyu Wang, Shijie Wang, Wenyu Liu, Zengqiang Zheng, Xinggang Wang

We present a simple, efficient, and scalable unfolding network, SAUNet, to simplify the network design with an adaptive alternate optimization framework for hyperspectral image (HSI) reconstruction.

Image Reconstruction

PD-Quant: Post-Training Quantization based on Prediction Difference Metric

1 code implementation CVPR 2023 Jiawei Liu, Lin Niu, Zhihang Yuan, Dawei Yang, Xinggang Wang, Wenyu Liu

It determines the quantization parameters by using the information of differences between network prediction before and after quantization.

Neural Network Compression Quantization

Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution

2 code implementations3 Dec 2022 Wentong Li, Wenyu Liu, Jianke Zhu, Miaomiao Cui, Risheng Yu, Xiansheng Hua, Lei Zhang

In contrast to fully supervised methods using pixel-wise mask labels, box-supervised instance segmentation takes advantage of simple box annotations, which has recently attracted increasing research attention.

Box-supervised Instance Segmentation

MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction

1 code implementation30 Aug 2022 Bencheng Liao, Shaoyu Chen, Xinggang Wang, Tianheng Cheng, Qian Zhang, Wenyu Liu, Chang Huang

High-definition (HD) map provides abundant and precise environmental information of the driving scene, serving as a fundamental and indispensable component for planning in autonomous driving system.

3D Lane Detection Autonomous Driving

Robust Multi-Object Tracking by Marginal Inference

no code implementations7 Aug 2022 Yifu Zhang, Chunyu Wang, Xinggang Wang, Wenjun Zeng, Wenyu Liu

To address the problem, we present an efficient approach to compute a marginal probability for each pair of objects in real time.

Multi-Object Tracking

When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition

1 code implementation23 Jul 2022 Bohan Li, Ye Yuan, Dingkang Liang, Xiao Liu, Zhilong Ji, Jinfeng Bai, Wenyu Liu, Xiang Bai

Recently, most handwritten mathematical expression recognition (HMER) methods adopt the encoder-decoder networks, which directly predict the markup sequences from formula images with the attention mechanism.

Optical Character Recognition (OCR)

Box-supervised Instance Segmentation with Level Set Evolution

2 code implementations19 Jul 2022 Wentong Li, Wenyu Liu, Jianke Zhu, Miaomiao Cui, Xiansheng Hua, Lei Zhang

A simple mask supervised SOLOv2 model is adapted to predict the instance-aware mask map as the level set for each instance.

Box-supervised Instance Segmentation

Improving Nighttime Driving-Scene Segmentation via Dual Image-adaptive Learnable Filters

2 code implementations4 Jul 2022 Wenyu Liu, Wentong Li, Jianke Zhu, Miaomiao Cui, Xuansong Xie, Lei Zhang

With DIAL-Filters, we design both unsupervised and supervised frameworks for nighttime driving-scene segmentation, which can be trained in an end-to-end manner.

Autonomous Driving Scene Segmentation

Warped Convolutional Networks: Bridge Homography to sl(3) algebra by Group Convolution

no code implementations23 Jun 2022 Xinrui Zhan, Yang Li, Wenyu Liu, Jianke Zhu

In this paper, we propose Warped Convolution Networks (WCN) to effectively learn and represent the homography by SL(3) group and sl(3) algebra with group convolution.

Homography Estimation Object Tracking

Polar Parametrization for Vision-based Surround-View 3D Detection

1 code implementation22 Jun 2022 Shaoyu Chen, Xinggang Wang, Tianheng Cheng, Qian Zhang, Chang Huang, Wenyu Liu

Based on Polar Parametrization, we propose a surround-view 3D DEtection TRansformer, named PolarDETR.

Inductive Bias

Featurized Query R-CNN

1 code implementation13 Jun 2022 Wenqiang Zhang, Tianheng Cheng, Xinggang Wang, Shaoyu Chen, Qian Zhang, Wenyu Liu

The query mechanism introduced in the DETR method is changing the paradigm of object detection and recently there are many query-based methods have obtained strong object detection performance.

object-detection Object Detection

Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer

1 code implementation9 Jun 2022 Shaoyu Chen, Tianheng Cheng, Xinggang Wang, Wenming Meng, Qian Zhang, Wenyu Liu

GKT leverages the geometric priors to guide the transformer to focus on discriminative regions and unfolds kernel features to generate BEV representation.

Autonomous Driving Representation Learning

Fast Dynamic Radiance Fields with Time-Aware Neural Voxels

1 code implementation30 May 2022 Jiemin Fang, Taoran Yi, Xinggang Wang, Lingxi Xie, Xiaopeng Zhang, Wenyu Liu, Matthias Nießner, Qi Tian

A multi-distance interpolation method is proposed and applied on voxel features to model both small and large motions.

Temporally Efficient Vision Transformer for Video Instance Segmentation

3 code implementations CVPR 2022 Shusheng Yang, Xinggang Wang, Yu Li, Yuxin Fang, Jiemin Fang, Wenyu Liu, Xun Zhao, Ying Shan

To effectively and efficiently model the crucial temporal information within a video clip, we propose a Temporally Efficient Vision Transformer (TeViT) for video instance segmentation (VIS).

Instance Segmentation Semantic Segmentation +1

TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation

3 code implementations CVPR 2022 Wenqiang Zhang, Zilong Huang, Guozhong Luo, Tao Chen, Xinggang Wang, Wenyu Liu, Gang Yu, Chunhua Shen

Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semantic segmentation on mobile devices.

Semantic Segmentation

Context-Sensitive Temporal Feature Learning for Gait Recognition

1 code implementation ICCV 2021 Xiaohu Huang, Duowang Zhu, Xinggang Wang, Hao Wang, Bo Yang, Botao He, Wenyu Liu, Bin Feng

Specifically, CSTL contains an adaptive temporal aggregation module that subsequently performs local relation modeling and global relation modeling to fuse the multi-scale features.

Multiview Gait Recognition

Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions

1 code implementation15 Dec 2021 Wenyu Liu, Gaofeng Ren, Runsheng Yu, Shi Guo, Jianke Zhu, Lei Zhang

Though deep learning-based object detection methods have achieved promising results on the conventional datasets, it is still challenging to locate objects from the low-quality images captured in adverse weather conditions.

Image Enhancement object-detection +1

Deep Level Set for Box-supervised Instance Segmentation in Aerial Images

no code implementations7 Dec 2021 Wentong Li, Yijie Chen, Wenyu Liu, Jianke Zhu

Instead of learning the pairwise affinity, the level set method with the carefully designed energy functions treats the object segmentation as curve evolution, which is able to accurately recover the object's boundaries and prevent the interference from the indistinguishable background and similar objects.

Box-supervised Instance Segmentation Semantic Segmentation

NeuSample: Neural Sample Field for Efficient View Synthesis

1 code implementation30 Nov 2021 Jiemin Fang, Lingxi Xie, Xinggang Wang, Xiaopeng Zhang, Wenyu Liu, Qi Tian

Neural radiance fields (NeRF) have shown great potentials in representing 3D scenes and synthesizing novel views, but the computational overhead of NeRF at the inference stage is still heavy.

Decoupling Visual-Semantic Feature Learning for Robust Scene Text Recognition

no code implementations24 Nov 2021 Changxu Cheng, Bohan Li, Qi Zheng, Yongpan Wang, Wenyu Liu

As a result, the learning of semantic features is prone to have a bias on the limited vocabulary of the training set, which is called vocabulary reliance.

Scene Text Recognition

VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild

no code implementations5 Aug 2021 Yifu Zhang, Chunyu Wang, Xinggang Wang, Wenyu Liu, Wenjun Zeng

We estimate 3D poses from the voxel representation by predicting whether each voxel contains a particular body joint.

Ranked #7 on 3D Multi-Person Pose Estimation on Panoptic (using extra training data)

3D Multi-Person Pose Estimation 3D Pose Estimation

What Makes for Hierarchical Vision Transformer?

no code implementations5 Jul 2021 Yuxin Fang, Xinggang Wang, Rui Wu, Wenyu Liu

Recent studies indicate that hierarchical Vision Transformer with a macro architecture of interleaved non-overlapped window-based self-attention \& shifted-window operation is able to achieve state-of-the-art performance in various visual recognition tasks, and challenges the ubiquitous convolutional neural networks (CNNs) using densely slid kernels.

Instance Segmentation object-detection +3

Tracking Instances as Queries

1 code implementation22 Jun 2021 Shusheng Yang, Yuxin Fang, Xinggang Wang, Yu Li, Ying Shan, Bin Feng, Wenyu Liu

Recently, query based deep networks catch lots of attention owing to their end-to-end pipeline and competitive results on several fundamental computer vision tasks, such as object detection, semantic segmentation, and instance segmentation.

Instance Segmentation object-detection +3

You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection

2 code implementations NeurIPS 2021 Yuxin Fang, Bencheng Liao, Xinggang Wang, Jiemin Fang, Jiyang Qi, Rui Wu, Jianwei Niu, Wenyu Liu

Can Transformer perform 2D object- and region-level recognition from a pure sequence-to-sequence perspective with minimal knowledge about the 2D spatial structure?

object-detection Object Detection

Instances as Queries

4 code implementations ICCV 2021 Yuxin Fang, Shusheng Yang, Xinggang Wang, Yu Li, Chen Fang, Ying Shan, Bin Feng, Wenyu Liu

The key insight of QueryInst is to leverage the intrinsic one-to-one correspondence in object queries across different stages, as well as one-to-one correspondence between mask RoI features and object queries in the same stage.

Ranked #13 on Object Detection on COCO-O (using extra training data)

Instance Segmentation object-detection +2

Crossover Learning for Fast Online Video Instance Segmentation

1 code implementation ICCV 2021 Shusheng Yang, Yuxin Fang, Xinggang Wang, Yu Li, Chen Fang, Ying Shan, Bin Feng, Wenyu Liu

For temporal information modeling in VIS, we present a novel crossover learning scheme that uses the instance feature in the current frame to pixel-wisely localize the same instance in other frames.

Instance Segmentation Semantic Segmentation +2

Scene Text Retrieval via Joint Text Detection and Similarity Learning

1 code implementation CVPR 2021 Hao Wang, Xiang Bai, Mingkun Yang, Shenggao Zhu, Jing Wang, Wenyu Liu

Such a task is usually realized by matching a query text to the recognized words, outputted by an end-to-end scene text spotter.

Retrieval Scene Text Detection +3

Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images

no code implementations CVPR 2021 Xinggang Wang, Jiapei Feng, Bin Hu, Qi Ding, Longjin Ran, Xiaoxin Chen, Wenyu Liu

Humans have a strong class-agnostic object segmentation ability and can outline boundaries of unknown objects precisely, which motivates us to propose a box-supervised class-agnostic object segmentation (BoxCaseg) based solution for weakly-supervised instance segmentation.

Ranked #5 on Box-supervised Instance Segmentation on COCO test-dev (using extra training data)

Box-supervised Instance Segmentation Multi-Task Learning +3

Half-Real Half-Fake Distillation for Class-Incremental Semantic Segmentation

no code implementations2 Apr 2021 Zilong Huang, Wentian Hao, Xinggang Wang, Mingyuan Tao, Jianqiang Huang, Wenyu Liu, Xian-Sheng Hua

Despite their success for semantic segmentation, convolutional neural networks are ill-equipped for incremental learning, \ie, adapting the original segmentation model as new classes are available but the initial training data is not retained.

Class-Incremental Semantic Segmentation Incremental Learning

Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition

no code implementations13 Jan 2021 Mengting Chen, Xinggang Wang, Heng Luo, Yifeng Geng, Wenyu Liu

By applying the proposed feature matching block in different layers of the few-shot recognition network, multi-scale information among the compared images can be incorporated into the final cascaded matching feature, which boosts the recognition performance further and generalizes better by learning on relationships.

Few-Shot Learning

ResizeMix: Mixing Data with Preserved Object Information and True Labels

1 code implementation21 Dec 2020 Jie Qin, Jiemin Fang, Qian Zhang, Wenyu Liu, Xingang Wang, Xinggang Wang

Especially, CutMix uses a simple but effective method to improve the classifiers by randomly cropping a patch from one image and pasting it on another image.

Data Augmentation Image Classification +2

Learning Global Structure Consistency for Robust Object Tracking

no code implementations26 Aug 2020 Bi Li, Chengquan Zhang, Zhibin Hong, Xu Tang, Jingtuo Liu, Junyu Han, Errui Ding, Wenyu Liu

Unlike many existing trackers that focus on modeling only the target, in this work, we consider the \emph{transient variations of the whole scene}.

Visual Object Tracking

Boundary-preserving Mask R-CNN

1 code implementation ECCV 2020 Tianheng Cheng, Xinggang Wang, Lichao Huang, Wenyu Liu

Besides, it is not surprising to observe that BMask R-CNN obtains more obvious improvement when the evaluation criterion requires better localization (e. g., AP$_{75}$) as shown in Fig. 1.

Instance Segmentation Semantic Segmentation

Deep multi-metric learning for text-independent speaker verification

1 code implementation17 Jul 2020 Jiwei Xu, Xinggang Wang, Bin Feng, Wenyu Liu

Text-independent speaker verification is an important artificial intelligence problem that has a wide spectrum of applications, such as criminal investigation, payment certification, and interest-based customer services.

Metric Learning Text-Independent Speaker Verification

Maximum Entropy Regularization and Chinese Text Recognition

no code implementations9 Jul 2020 Changxu Cheng, Wuheng Xu, Xiang Bai, Bin Feng, Wenyu Liu

Chinese text recognition is more challenging than Latin text due to the large amount of fine-grained Chinese characters and the great imbalance over classes, which causes a serious overfitting problem.

Fine-Grained Image Classification

FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search

2 code implementations21 Jun 2020 Jiemin Fang, Yuzhu Sun, Qian Zhang, Kangjian Peng, Yuan Li, Wenyu Liu, Xinggang Wang

In this paper, we propose a Fast Network Adaptation (FNA++) method, which can adapt both the architecture and parameters of a seed network (e. g. an ImageNet pre-trained network) to become a network with different depths, widths, or kernel sizes via a parameter remapping technique, making it possible to use NAS for segmentation and detection tasks a lot more efficiently.

Image Classification Neural Architecture Search +4

FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking

29 code implementations4 Apr 2020 Yifu Zhang, Chunyu Wang, Xinggang Wang, Wen-Jun Zeng, Wenyu Liu

Formulating MOT as multi-task learning of object detection and re-ID in a single network is appealing since it allows joint optimization of the two tasks and enjoys high computation efficiency.

 Ranked #1 on Multi-Object Tracking on 2DMOT15 (using extra training data)

Fairness Multi-Object Tracking +3

Deep Learning-based Detection for COVID-19 from Chest CT using Weak Label

1 code implementation medRxiv 2020 Chuansheng Zheng, Xianbo Deng, Qing Fu, Qiang Zhou, Jiapei Feng, Hui Ma, Wenyu Liu, Xinggang Wang

Our weakly-supervised deep learning model can accurately predict the COVID-19 infectious probability in chest CT volumes without the need for annotating the lesions for training.

COVID-19 Diagnosis Specificity

AlignSeg: Feature-Aligned Segmentation Networks

1 code implementation24 Feb 2020 Zilong Huang, Yunchao Wei, Xinggang Wang, Wenyu Liu, Thomas S. Huang, Humphrey Shi

Aggregating features in terms of different convolutional blocks or contextual embeddings has been proven to be an effective way to strengthen feature representations for semantic segmentation.

Semantic Segmentation

Fast Neural Network Adaptation via Parameter Remapping and Architecture Search

no code implementations ICLR 2020 Jiemin Fang, Yuzhu Sun, Kangjian Peng, Qian Zhang, Yuan Li, Wenyu Liu, Xinggang Wang

In our experiments, we conduct FNA on MobileNetV2 to obtain new networks for both segmentation and detection that clearly out-perform existing networks designed both manually and by NAS.

Image Classification Neural Architecture Search +3

Diversity Transfer Network for Few-Shot Learning

1 code implementation31 Dec 2019 Mengting Chen, Yuxin Fang, Xinggang Wang, Heng Luo, Yifeng Geng, Xin-Yu Zhang, Chang Huang, Wenyu Liu, Bo wang

The learning problem of the sample generation (i. e., diversity transfer) is solved via minimizing an effective meta-classification loss in a single-stage network, instead of the generative loss in previous works.

Few-Shot Learning

Patch Aggregator for Scene Text Script Identification

no code implementations9 Dec 2019 Changxu Cheng, Qiuhui Huang, Xiang Bai, Bin Feng, Wenyu Liu

Script identification in the wild is of great importance in a multi-lingual robust-reading system.


All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting

no code implementations21 Nov 2019 Hao Wang, Pu Lu, HUI ZHANG, Mingkun Yang, Xiang Bai, Yongchao Xu, Mengchao He, Yongpan Wang, Wenyu Liu

Recently, end-to-end text spotting that aims to detect and recognize text from cluttered images simultaneously has received particularly growing interest in computer vision.

Instance Segmentation Scene Text Detection +3

Deep High-Resolution Representation Learning for Visual Recognition

40 code implementations20 Aug 2019 Jingdong Wang, Ke Sun, Tianheng Cheng, Borui Jiang, Chaorui Deng, Yang Zhao, Dong Liu, Yadong Mu, Mingkui Tan, Xinggang Wang, Wenyu Liu, Bin Xiao

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection.

 Ranked #1 on Object Detection on COCO test-dev (Hardware Burden metric)

Dichotomous Image Segmentation Face Alignment +7

DeepExposure: Learning to Expose Photos with Asynchronously Reinforced Adversarial Learning

no code implementations NeurIPS 2018 Runsheng Yu, Wenyu Liu, Yasen Zhang, Zhi Qu, Deli Zhao, Bo Zhang

Based on these sub-images, a local exposure for each sub-image is automatically learned by virtue of policy network sequentially while the reward of learning is globally designed for striking a balance of overall exposures.

CCNet: Criss-Cross Attention for Semantic Segmentation

4 code implementations ICCV 2019 Zilong Huang, Xinggang Wang, Yunchao Wei, Lichao Huang, Humphrey Shi, Wenyu Liu, Thomas S. Huang

Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11x less GPU memory usage.

Ranked #7 on Semantic Segmentation on FoodSeg103 (using extra training data)

Human Parsing Instance Segmentation +6

Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-identification

no code implementations ECCV 2018 Cheng Wang, Qian Zhang, Chang Huang, Wenyu Liu, Xinggang Wang

We propose a novel deep network called Mancs that solves the person re-identification problem from the following aspects: fully utilizing the attention mechanism for the person misalignment problem and properly sampling for the ranking loss to obtain more stable person representation.

Person Re-Identification

Weakly Supervised Region Proposal Network and Object Detection

no code implementations ECCV 2018 Peng Tang, Xinggang Wang, Angtian Wang, Yongluan Yan, Wenyu Liu, Junzhou Huang, Alan Yuille

The Convolutional Neural Network (CNN) based region proposal generation method (i. e. region proposal network), trained using bounding box annotations, is an essential component in modern fully supervised object detectors.

object-detection Region Proposal +1

PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

4 code implementations9 Jul 2018 Peng Tang, Xinggang Wang, Song Bai, Wei Shen, Xiang Bai, Wenyu Liu, Alan Yuille

The iterative instance classifier refinement is implemented online using multiple streams in convolutional neural networks, where the first is an MIL network and the others are for instance classifier refinement supervised by the preceding one.

Multiple Instance Learning object-detection +2

Learning to Update for Object Tracking with Recurrent Meta-learner

no code implementations19 Jun 2018 Bi Li, Wenxuan Xie, Wen-Jun Zeng, Wenyu Liu

Generally, model update is formulated as an online learning problem where a target model is learned over the online training set.

Meta-Learning Visual Object Tracking +1

Weakly-Supervised Semantic Segmentation Network With Deep Seeded Region Growing

1 code implementation CVPR 2018 Zilong Huang, Xinggang Wang, Jiasi Wang, Wenyu Liu, Jingdong Wang

Inspired by the traditional image segmentation methods of seeded region growing, we propose to train a semantic segmentation network starting from the discriminative regions and progressively increase the pixel-level supervision using by seeded region growing.

Ranked #28 on Weakly-Supervised Semantic Segmentation on COCO 2014 val (using extra training data)

Image Segmentation Weakly supervised Semantic Segmentation +1

Auto-Encoder Guided GAN for Chinese Calligraphy Synthesis

no code implementations27 Jun 2017 Pengyuan Lyu, Xiang Bai, Cong Yao, Zhen Zhu, Tengteng Huang, Wenyu Liu

In this paper, we investigate the Chinese calligraphy synthesis problem: synthesizing Chinese calligraphy images with specified style from standard font(eg.

Image-to-Image Translation Translation

Point Linking Network for Object Detection

no code implementations12 Jun 2017 Xinggang Wang, Kaibing Chen, Zilong Huang, Cong Yao, Wenyu Liu

The deep ConvNets based object detectors mainly focus on regressing the coordinates of bounding box, e. g., Faster-R-CNN, YOLO and SSD.

object-detection Object Detection

Deep Patch Learning for Weakly Supervised Object Classification and Discovery

1 code implementation6 May 2017 Peng Tang, Xinggang Wang, Zilong Huang, Xiang Bai, Wenyu Liu

Patch-level image representation is very important for object classification and detection, since it is robust to spatial transformation, scale variation, and cluttered background.

Classification General Classification +2

Multiple Instance Detection Network with Online Instance Classifier Refinement

4 code implementations CVPR 2017 Peng Tang, Xinggang Wang, Xiang Bai, Wenyu Liu

We propose a novel online instance classifier refinement algorithm to integrate MIL and the instance classifier refinement procedure into a single deep network, and train the network end-to-end with only image-level supervision, i. e., without object location information.

Multiple Instance Learning object-detection +2

TextBoxes: A Fast Text Detector with a Single Deep Neural Network

4 code implementations21 Nov 2016 Minghui Liao, Baoguang Shi, Xiang Bai, Xinggang Wang, Wenyu Liu

This paper presents an end-to-end trainable fast scene text detector, named TextBoxes, which detects scene text with both high accuracy and efficiency in a single network forward pass, involving no post-process except for a standard non-maximum suppression.

Revisiting Multiple Instance Neural Networks

no code implementations8 Oct 2016 Xinggang Wang, Yongluan Yan, Peng Tang, Xiang Bai, Wenyu Liu

We propose a new multiple instance neural network to learn bag representations, which is different from the existing multiple instance neural networks that focus on estimating instance label.

Multiple Instance Learning Weakly-supervised Learning

Deep FisherNet for Object Classification

no code implementations31 Jul 2016 Peng Tang, Xinggang Wang, Baoguang Shi, Xiang Bai, Wenyu Liu, Zhuowen Tu

Our proposed FisherNet combines convolutional neural network training and Fisher Vector encoding in a single end-to-end structure.

Classification General Classification +1

Deep Regression for Face Alignment

no code implementations18 Sep 2014 Baoguang Shi, Xiang Bai, Wenyu Liu, Jingdong Wang

In this paper, we present a deep regression approach for face alignment.

Face Alignment regression

Strokelets: A Learned Multi-Scale Representation for Scene Text Recognition

no code implementations CVPR 2014 Cong Yao, Xiang Bai, Baoguang Shi, Wenyu Liu

Driven by the wide range of applications, scene text detection and recognition have become active research topics in computer vision.

Scene Text Detection Scene Text Recognition +1

Fusion with Diffusion for Robust Visual Tracking

no code implementations NeurIPS 2012 Yu Zhou, Xiang Bai, Wenyu Liu, Longin J. Latecki

A key feature of our approach is that the time complexity of the dif-fusion on the TPG is the same as the diffusion process on each of the original graphs, Moreover, it is not necessary to explicitly construct the TPG in our frame-work.

Clustering Visual Tracking

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