Search Results for author: Xing Wei

Found 33 papers, 16 papers with code

Topology-Preserving Class-Incremental Learning

no code implementations ECCV 2020 Xiaoyu Tao, Xinyuan Chang, Xiaopeng Hong, Xing Wei, Yihong Gong

A well-known issue for class-incremental learning is the catastrophic forgetting phenomenon, where the network's recognition performance on old classes degrades severely when incrementally learning new classes.

Class Incremental Learning Incremental Learning

CEAT: Continual Expansion and Absorption Transformer for Non-Exemplar Class-Incremental Learning

no code implementations11 Mar 2024 Xinyuan Gao, Songlin Dong, Yuhang He, Xing Wei, Yihong Gong

Besides, to address the classifier bias towards the new classes, we propose a novel approach to generate the pseudo-features to correct the classifier.

Class Incremental Learning Incremental Learning

ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe

1 code implementation28 Dec 2023 Yifan Bai, Zeyang Zhao, Yihong Gong, Xing Wei

We present ARTrackV2, which integrates two pivotal aspects of tracking: determining where to look (localization) and how to describe (appearance analysis) the target object across video frames.

Object Template Matching +2

MachMap: End-to-End Vectorized Solution for Compact HD-Map Construction

2 code implementations17 Jun 2023 Limeng Qiao, Yongchao Zheng, Peng Zhang, Wenjie Ding, Xi Qiu, Xing Wei, Chi Zhang

This report introduces the 1st place winning solution for the Autonomous Driving Challenge 2023 - Online HD-map Construction.

Autonomous Driving

Knowledge Restore and Transfer for Multi-label Class-Incremental Learning

1 code implementation ICCV 2023 Songlin Dong, Haoyu Luo, Yuhang He, Xing Wei, Yihong Gong

Current class-incremental learning research mainly focuses on single-label classification tasks while multi-label class-incremental learning (MLCIL) with more practical application scenarios is rarely studied.

Class Incremental Learning Incremental Learning +1

Deep Dynamic Scene Deblurring from Optical Flow

no code implementations18 Jan 2023 Jiawei Zhang, Jinshan Pan, Daoye Wang, Shangchen Zhou, Xing Wei, Furong Zhao, Jianbo Liu, Jimmy Ren

In this paper, we explore optical flow to remove dynamic scene blur by using the multi-scale spatially variant recurrent neural network (RNN).

Deblurring Optical Flow Estimation

Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation

1 code implementation ICCV 2023 Heng Zhao, Shenxing Wei, Dahu Shi, Wenming Tan, Zheyang Li, Ye Ren, Xing Wei, Yi Yang, ShiLiang Pu

Taking the symmetry properties of objects into consideration, we design a symmetry-aware matching loss to facilitate the learning of dense point-wise geometry features and improve the performance considerably.

6D Pose Estimation 6D Pose Estimation using RGB +3

DKT: Diverse Knowledge Transfer Transformer for Class Incremental Learning

no code implementations CVPR 2023 Xinyuan Gao, Yuhang He, Songlin Dong, Jie Cheng, Xing Wei, Yihong Gong

Deep neural networks suffer from catastrophic forgetting in class incremental learning, where the classification accuracy of old classes drastically deteriorates when the networks learn the knowledge of new classes.

Class Incremental Learning General Knowledge +2

IR2Net: Information Restriction and Information Recovery for Accurate Binary Neural Networks

1 code implementation6 Oct 2022 Ping Xue, Yang Lu, Jingfei Chang, Xing Wei, Zhen Wei

In contrast, considering the limited learning ability and information loss caused by the limited representational capability of BNNs, we propose IR$^2$Net to stimulate the potential of BNNs and improve the network accuracy by restricting the input information and recovering the feature information, including: 1) information restriction: for a BNN, by evaluating the learning ability on the input information, discarding some of the information it cannot focus on, and limiting the amount of input information to match its learning ability; 2) information recovery: due to the information loss in forward propagation, the output feature information of the network is not enough to support accurate classification.

Binarization Quantization

End-to-End Multi-Person Pose Estimation With Transformers

1 code implementation CVPR 2022 Dahu Shi, Xing Wei, Liangqi Li, Ye Ren, Wenming Tan

Current methods of multi-person pose estimation typically treat the localization and association of body joints separately.

Multi-Person Pose Estimation

Scene-Adaptive Attention Network for Crowd Counting

no code implementations31 Dec 2021 Xing Wei, Yuanrui Kang, Jihao Yang, Yunfeng Qiu, Dahu Shi, Wenming Tan, Yihong Gong

First of all, we design a deformable attention in-built Transformer backbone, which learns adaptive feature representations with deformable sampling locations and dynamic attention weights.

Crowd Counting

SOIT: Segmenting Objects with Instance-Aware Transformers

1 code implementation21 Dec 2021 Xiaodong Yu, Dahu Shi, Xing Wei, Ye Ren, Tingqun Ye, Wenming Tan

The pixel-wise mask, especially, is embedded by a group of parameters to construct a lightweight instance-aware transformer.

Instance Segmentation Segmentation +1

Anomaly Detection via Self-organizing Map

1 code implementation21 Jul 2021 Ning li, Kaitao Jiang, Zhiheng Ma, Xing Wei, Xiaopeng Hong, Yihong Gong

Anomaly detection plays a key role in industrial manufacturing for product quality control.

Unsupervised Anomaly Detection

Direct Measure Matching for Crowd Counting

no code implementations4 Jul 2021 Hui Lin, Xiaopeng Hong, Zhiheng Ma, Xing Wei, Yunfeng Qiu, YaoWei Wang, Yihong Gong

Second, we derive a semi-balanced form of Sinkhorn divergence, based on which a Sinkhorn counting loss is designed for measure matching.

Crowd Counting

Self-Distribution Binary Neural Networks

1 code implementation3 Mar 2021 Ping Xue, Yang Lu, Jingfei Chang, Xing Wei, Zhen Wei

In this work, we study the binary neural networks (BNNs) of which both the weights and activations are binary (i. e., 1-bit representation).

Quantization

Efficient Deep Image Denoising via Class Specific Convolution

no code implementations2 Mar 2021 Lu Xu, Jiawei Zhang, Xuanye Cheng, Feng Zhang, Xing Wei, Jimmy Ren

In this paper, we propose an efficient deep neural network for image denoising based on pixel-wise classification.

Image Denoising

Towards a Universal Model for Cross-Dataset Crowd Counting

no code implementations ICCV 2021 Zhiheng Ma, Xiaopeng Hong, Xing Wei, Yunfeng Qiu, Yihong Gong

This paper proposes to handle the practical problem of learning a universal model for crowd counting across scenes and datasets.

Crowd Counting

UCP: Uniform Channel Pruning for Deep Convolutional Neural Networks Compression and Acceleration

no code implementations3 Oct 2020 Jingfei Chang, Yang Lu, Ping Xue, Xing Wei, Zhen Wei

For ResNet with bottlenecks, we use the pruning method with traditional CNN to trim the 3x3 convolutional layer in the middle of the blocks.

Image Classification

Inertial and gravity wave transmissions near radiative-convective boundaries

no code implementations1 Aug 2020 Tao Cai, Cong Yu, Xing Wei

Two configurations have been considered: waves propagate from the convective layer to the radiative stratified stable layer, or In this paper, we study inertial and gravity wave transmissions near radiative-convective boundaries on the {\it f}-plane.

Fluid Dynamics Solar and Stellar Astrophysics

Beyond Universal Person Re-ID Attack

no code implementations30 Oct 2019 Wenjie Ding, Xing Wei, Rongrong Ji, Xiaopeng Hong, Qi Tian, Yihong Gong

We propose a \emph{more universal} adversarial perturbation (MUAP) method for both image-agnostic and model-insensitive person Re-ID attack.

General Classification Person Re-Identification

Person Re-identification in Aerial Imagery

1 code implementation14 Aug 2019 Shizhou Zhang, Qi Zhang, Yifei Yang, Xing Wei, Peng Wang, Bingliang Jiao, Yanning Zhang

Our method can learn a discriminative and compact feature representation for ReID in aerial imagery and can be trained in an end-to-end fashion efficiently.

object-detection Object Detection +1

Bayesian Loss for Crowd Count Estimation with Point Supervision

3 code implementations ICCV 2019 Zhiheng Ma, Xing Wei, Xiaopeng Hong, Yihong Gong

In crowd counting datasets, each person is annotated by a point, which is usually the center of the head.

Crowd Counting

Reinforcement Learning Based Emotional Editing Constraint Conversation Generation

no code implementations17 Apr 2019 Jia Li, Xiao Sun, Xing Wei, Changliang Li, Jian-Hua Tao

In recent years, the generation of conversation content based on deep neural networks has attracted many researchers.

Multi-Task Learning reinforcement-learning +1

Downhole Track Detection via Multiscale Conditional Generative Adversarial Nets

no code implementations17 Apr 2019 Jia Li, Xing Wei, Guoqiang Yang, Xiao Sun, Changliang Li

A multiscale shared convolution structure is adopted in the discriminator network to further supervise training the generator.

Autonomous Driving Generative Adversarial Network

Embedding Electronic Health Records for Clinical Information Retrieval

no code implementations13 Nov 2018 Xing Wei, Carsten Eickhoff

Neural network representation learning frameworks have recently shown to be highly effective at a wide range of tasks ranging from radiography interpretation via data-driven diagnostics to clinical decision support.

Information Retrieval Representation Learning +1

Grassmann Pooling as Compact Homogeneous Bilinear Pooling for Fine-Grained Visual Classification

no code implementations ECCV 2018 Xing Wei, Yue Zhang, Yihong Gong, Jiawei Zhang, Nanning Zheng

The reason is that the bilinear feature matrix is sensitive to the magnitudes and correlations of local CNN feature elements which can be measured by its singular values.

Fine-Grained Image Classification Fine-Grained Visual Recognition +1

Kernelized Subspace Pooling for Deep Local Descriptors

no code implementations CVPR 2018 Xing Wei, Yue Zhang, Yihong Gong, Nanning Zheng

Experimental results on several patch matching benchmarks show that our method outperforms the state-of-the-arts significantly.

Patch Matching

Superpixel Hierarchy

1 code implementation20 May 2016 Xing Wei, Qingxiong Yang, Yihong Gong, Ming-Hsuan Yang, Narendra Ahuja

Quantitative and qualitative evaluation on a number of computer vision applications was conducted, demonstrating that the proposed method is the top performer.

Image Segmentation Segmentation +2

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