Search Results for author: Baochang Zhang

Found 69 papers, 20 papers with code

Bi-level Doubly Variational Learning for Energy-based Latent Variable Models

no code implementations24 Mar 2022 Ge Kan, Jinhu Lü, Tian Wang, Baochang Zhang, Aichun Zhu, Lei Huang, Guodong Guo, Hichem Snoussi

In this paper, we propose Bi-level doubly variational learning (BiDVL), which is based on a new bi-level optimization framework and two tractable variational distributions to facilitate learning EBLVMs.

Image Generation Image Reconstruction +1

TerViT: An Efficient Ternary Vision Transformer

no code implementations20 Jan 2022 Sheng Xu, Yanjing Li, Teli Ma, Bohan Zeng, Baochang Zhang, Peng Gao, Jinhu Lv

Vision transformers (ViTs) have demonstrated great potential in various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices.

Associative Adversarial Learning Based on Selective Attack

no code implementations28 Dec 2021 Runqi Wang, Xiaoyue Duan, Baochang Zhang, Song Xue, Wentao Zhu, David Doermann, Guodong Guo

We show that our method improves the recognition accuracy of adversarial training on ImageNet by 8. 32% compared with the baseline.

Adversarial Robustness Few-Shot Learning +1

Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue

1 code implementation15 Dec 2021 Shuwei Shao, Zhongcai Pei, Weihai Chen, Wentao Zhu, Xingming Wu, Dianmin Sun, Baochang Zhang

Recently, self-supervised learning technology has been applied to calculate depth and ego-motion from monocular videos, achieving remarkable performance in autonomous driving scenarios.

Depth Estimation Motion Estimation +1

POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing

no code implementations26 Nov 2021 Sheng Xu, Yanjing Li, Junhe Zhao, Baochang Zhang, Guodong Guo

Real-time point cloud processing is fundamental for lots of computer vision tasks, while still challenged by the computational problem on resource-limited edge devices.

IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization

1 code implementation17 Nov 2021 Yunshan Zhong, Mingbao Lin, Gongrui Nan, Jianzhuang Liu, Baochang Zhang, Yonghong Tian, Rongrong Ji

In this paper, we observe an interesting phenomenon of intra-class heterogeneity in real data and show that existing methods fail to retain this property in their synthetic images, which causes a limited performance increase.


NENet: Monocular Depth Estimation via Neural Ensembles

no code implementations16 Nov 2021 Shuwei Shao, Ran Li, Zhongcai Pei, Zhong Liu, Weihai Chen, Wentao Zhu, Xingming Wu, Baochang Zhang

In particular, our method improves previous state-of-the-art methods from 0. 365 to 0. 349 on the metric RMSE on the NYU dataset.

Ensemble Learning Monocular Depth Estimation

Cogradient Descent for Dependable Learning

no code implementations20 Jun 2021 Runqi Wang, Baochang Zhang, Li'an Zhuo, Qixiang Ye, David Doermann

Conventional gradient descent methods compute the gradients for multiple variables through the partial derivative.

Image Inpainting Image Reconstruction +1

Layer-Wise Searching for 1-Bit Detectors

no code implementations CVPR 2021 Sheng Xu, Junhe Zhao, Jinhu Lu, Baochang Zhang, Shumin Han, David Doermann

At each layer, it exploits a differentiable binarization search (DBS) to minimize the angular error in a student-teacher framework.


Oriented Object Detection with Transformer

no code implementations6 Jun 2021 Teli Ma, Mingyuan Mao, Honghui Zheng, Peng Gao, Xiaodi Wang, Shumin Han, Errui Ding, Baochang Zhang, David Doermann

Object detection with Transformers (DETR) has achieved a competitive performance over traditional detectors, such as Faster R-CNN.

Object Detection

Dual-stream Network for Visual Recognition

no code implementations NeurIPS 2021 Mingyuan Mao, Renrui Zhang, Honghui Zheng, Peng Gao, Teli Ma, Yan Peng, Errui Ding, Baochang Zhang, Shumin Han

Transformers with remarkable global representation capacities achieve competitive results for visual tasks, but fail to consider high-level local pattern information in input images.

Image Classification Instance Segmentation +2

SiMaN: Sign-to-Magnitude Network Binarization

1 code implementation16 Feb 2021 Mingbao Lin, Rongrong Ji, Zihan Xu, Baochang Zhang, Fei Chao, Mingliang Xu, Chia-Wen Lin, Ling Shao

In this paper, we show that our weight binarization provides an analytical solution by encoding high-magnitude weights into +1s, and 0s otherwise.


Multi-UAV Mobile Edge Computing and Path Planning Platform based on Reinforcement Learning

no code implementations3 Feb 2021 Huan Chang, Yicheng Chen, Baochang Zhang, David Doermann

Unmanned Aerial vehicles (UAVs) are widely used as network processors in mobile networks, but more recently, UAVs have been used in Mobile Edge Computing as mobile servers.

Edge-computing reinforcement-learning

Aha! Adaptive History-Driven Attack for Decision-Based Black-Box Models

no code implementations ICCV 2021 Jie Li, Rongrong Ji, Peixian Chen, Baochang Zhang, Xiaopeng Hong, Ruixin Zhang, Shaoxin Li, Jilin Li, Feiyue Huang, Yongjian Wu

A common practice is to start from a large perturbation and then iteratively reduce it with a deterministic direction and a random one while keeping it adversarial.

Dimensionality Reduction

IDARTS: Interactive Differentiable Architecture Search

no code implementations ICCV 2021 Song Xue, Runqi Wang, Baochang Zhang, Tian Wang, Guodong Guo, David Doermann

Differentiable Architecture Search (DARTS) improves the efficiency of architecture search by learning the architecture and network parameters end-to-end.

Fast Class-wise Updating for Online Hashing

no code implementations1 Dec 2020 Mingbao Lin, Rongrong Ji, Xiaoshuai Sun, Baochang Zhang, Feiyue Huang, Yonghong Tian, DaCheng Tao

To achieve fast online adaptivity, a class-wise updating method is developed to decompose the binary code learning and alternatively renew the hash functions in a class-wise fashion, which well addresses the burden on large amounts of training batches.

online learning

A Review of Recent Advances of Binary Neural Networks for Edge Computing

no code implementations24 Nov 2020 Wenyu Zhao, Teli Ma, Xuan Gong, Baochang Zhang, David Doermann

Edge computing is promising to become one of the next hottest topics in artificial intelligence because it benefits various evolving domains such as real-time unmanned aerial systems, industrial applications, and the demand for privacy protection.

Edge-computing Neural Architecture Search +2

PAMS: Quantized Super-Resolution via Parameterized Max Scale

1 code implementation ECCV 2020 Huixia Li, Chenqian Yan, Shaohui Lin, Xiawu Zheng, Yuchao Li, Baochang Zhang, Fan Yang, Rongrong Ji

Specifically, most state-of-the-art SR models without batch normalization have a large dynamic quantization range, which also serves as another cause of performance drop.

Quantization Super-Resolution +1

Rotated Binary Neural Network

2 code implementations NeurIPS 2020 Mingbao Lin, Rongrong Ji, Zihan Xu, Baochang Zhang, Yan Wang, Yongjian Wu, Feiyue Huang, Chia-Wen Lin

In this paper, for the first time, we explore the influence of angular bias on the quantization error and then introduce a Rotated Binary Neural Network (RBNN), which considers the angle alignment between the full-precision weight vector and its binarized version.

Binarization Quantization

The 1st Tiny Object Detection Challenge:Methods and Results

1 code implementation16 Sep 2020 Xuehui Yu, Zhenjun Han, Yuqi Gong, Nan Jiang, Jian Zhao, Qixiang Ye, Jie Chen, Yuan Feng, Bin Zhang, Xiaodi Wang, Ying Xin, Jingwei Liu, Mingyuan Mao, Sheng Xu, Baochang Zhang, Shumin Han, Cheng Gao, Wei Tang, Lizuo Jin, Mingbo Hong, Yuchao Yang, Shuiwang Li, Huan Luo, Qijun Zhao, Humphrey Shi

The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection.

Human Detection Object Detection

Binarized Neural Architecture Search for Efficient Object Recognition

no code implementations8 Sep 2020 Hanlin Chen, Li'an Zhuo, Baochang Zhang, Xiawu Zheng, Jianzhuang Liu, Rongrong Ji, David Doermann, Guodong Guo

In this paper, binarized neural architecture search (BNAS), with a search space of binarized convolutions, is introduced to produce extremely compressed models to reduce huge computational cost on embedded devices for edge computing.

Edge-computing Face Recognition +2

Anti-Bandit Neural Architecture Search for Model Defense

1 code implementation ECCV 2020 Hanlin Chen, Baochang Zhang, Song Xue, Xuan Gong, Hong Liu, Rongrong Ji, David Doermann

Deep convolutional neural networks (DCNNs) have dominated as the best performers in machine learning, but can be challenged by adversarial attacks.

Denoising Neural Architecture Search

iffDetector: Inference-aware Feature Filtering for Object Detection

1 code implementation23 Jun 2020 Mingyuan Mao, Yuxin Tian, Baochang Zhang, Qixiang Ye, Wanquan Liu, Guodong Guo, David Doermann

In this paper, we propose a new feature optimization approach to enhance features and suppress background noise in both the training and inference stages.

Object Detection

Cogradient Descent for Bilinear Optimization

no code implementations CVPR 2020 Li'an Zhuo, Baochang Zhang, Linlin Yang, Hanlin Chen, Qixiang Ye, David Doermann, Guodong Guo, Rongrong Ji

Conventional learning methods simplify the bilinear model by regarding two intrinsically coupled factors independently, which degrades the optimization procedure.

Image Reconstruction Network Pruning

CP-NAS: Child-Parent Neural Architecture Search for Binary Neural Networks

no code implementations30 Apr 2020 Li'an Zhuo, Baochang Zhang, Hanlin Chen, Linlin Yang, Chen Chen, Yanjun Zhu, David Doermann

To this end, a Child-Parent (CP) model is introduced to a differentiable NAS to search the binarized architecture (Child) under the supervision of a full-precision model (Parent).

Neural Architecture Search

NAS-Count: Counting-by-Density with Neural Architecture Search

no code implementations ECCV 2020 Yutao Hu, Xiao-Long Jiang, Xuhui Liu, Baochang Zhang, Jungong Han, Xian-Bin Cao, David Doermann

Most of the recent advances in crowd counting have evolved from hand-designed density estimation networks, where multi-scale features are leveraged to address the scale variation problem, but at the expense of demanding design efforts.

Crowd Counting Density Estimation +1

HRank: Filter Pruning using High-Rank Feature Map

2 code implementations CVPR 2020 Mingbao Lin, Rongrong Ji, Yan Wang, Yichen Zhang, Baochang Zhang, Yonghong Tian, Ling Shao

The principle behind our pruning is that low-rank feature maps contain less information, and thus pruned results can be easily reproduced.

Network Pruning

Channel Pruning via Automatic Structure Search

1 code implementation23 Jan 2020 Mingbao Lin, Rongrong Ji, Yuxin Zhang, Baochang Zhang, Yongjian Wu, Yonghong Tian

In this paper, we propose a new channel pruning method based on artificial bee colony algorithm (ABC), dubbed as ABCPruner, which aims to efficiently find optimal pruned structure, i. e., channel number in each layer, rather than selecting "important" channels as previous works did.

Variational Structured Semantic Inference for Diverse Image Captioning

no code implementations NeurIPS 2019 Fuhai Chen, Rongrong Ji, Jiayi Ji, Xiaoshuai Sun, Baochang Zhang, Xuri Ge, Yongjian Wu, Feiyue Huang, Yan Wang

To model these two inherent diversities in image captioning, we propose a Variational Structured Semantic Inferring model (termed VSSI-cap) executed in a novel structured encoder-inferer-decoder schema.

Image Captioning

GBCNs: Genetic Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs

no code implementations25 Nov 2019 Chunlei Liu, Wenrui Ding, Yuan Hu, Baochang Zhang, Jianzhuang Liu, Guodong Guo

The BGA method is proposed to modify the binary process of GBCNs to alleviate the local minima problem, which can significantly improve the performance of 1-bit DCNNs.

Face Recognition Object Recognition +1

Binarized Neural Architecture Search

1 code implementation25 Nov 2019 Hanlin Chen, Li'an Zhuo, Baochang Zhang, Xiawu Zheng, Jianzhuang Liu, David Doermann, Rongrong Ji

A variant, binarized neural architecture search (BNAS), with a search space of binarized convolutions, can produce extremely compressed models.

Neural Architecture Search

Aggregation Signature for Small Object Tracking

no code implementations24 Oct 2019 Chunlei Liu, Wenrui Ding, Jinyu Yang, Vittorio Murino, Baochang Zhang, Jungong Han, Guodong Guo

In this paper, we propose a novel aggregation signature suitable for small object tracking, especially aiming for the challenge of sudden and large drift.

Object Tracking

Circulant Binary Convolutional Networks: Enhancing the Performance of 1-bit DCNNs with Circulant Back Propagation

no code implementations CVPR 2019 Chunlei Liu, Wenrui Ding, Xin Xia, Baochang Zhang, Jiaxin Gu, Jianzhuang Liu, Rongrong Ji, David Doermann

The CiFs can be easily incorporated into existing deep convolutional neural networks (DCNNs), which leads to new Circulant Binary Convolutional Networks (CBCNs).

Semantic-aware Image Deblurring

no code implementations9 Oct 2019 Fuhai Chen, Rongrong Ji, Chengpeng Dai, Xiaoshuai Sun, Chia-Wen Lin, Jiayi Ji, Baochang Zhang, Feiyue Huang, Liujuan Cao

Specially, we propose a novel Structured-Spatial Semantic Embedding model for image deblurring (termed S3E-Deblur), which introduces a novel Structured-Spatial Semantic tree model (S3-tree) to bridge two basic tasks in computer vision: image deblurring (ImD) and image captioning (ImC).

Deblurring Image Captioning +1

RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs

no code implementations21 Aug 2019 Chunlei Liu, Wenrui Ding, Xin Xia, Yuan Hu, Baochang Zhang, Jianzhuang Liu, Bohan Zhuang, Guodong Guo

Binarized convolutional neural networks (BCNNs) are widely used to improve memory and computation efficiency of deep convolutional neural networks (DCNNs) for mobile and AI chips based applications.

Binarization Object Tracking

Bayesian Optimized 1-Bit CNNs

no code implementations ICCV 2019 Jiaxin Gu, Junhe Zhao, Xiao-Long Jiang, Baochang Zhang, Jianzhuang Liu, Guodong Guo, Rongrong Ji

Deep convolutional neural networks (DCNNs) have dominated the recent developments in computer vision through making various record-breaking models.

Interpretable Neural Network Decoupling

no code implementations ECCV 2020 Yuchao Li, Rongrong Ji, Shaohui Lin, Baochang Zhang, Chenqian Yan, Yongjian Wu, Feiyue Huang, Ling Shao

More specifically, we introduce a novel architecture controlling module in each layer to encode the network architecture by a vector.

Supervised Online Hashing via Similarity Distribution Learning

no code implementations31 May 2019 Mingbao Lin, Rongrong Ji, Shen Chen, Feng Zheng, Xiaoshuai Sun, Baochang Zhang, Liujuan Cao, Guodong Guo, Feiyue Huang

In this paper, we propose to model the similarity distributions between the input data and the hashing codes, upon which a novel supervised online hashing method, dubbed as Similarity Distribution based Online Hashing (SDOH), is proposed, to keep the intrinsic semantic relationship in the produced Hamming space.

Dynamic Distribution Pruning for Efficient Network Architecture Search

1 code implementation28 May 2019 Xiawu Zheng, Rongrong Ji, Lang Tang, Yan Wan, Baochang Zhang, Yongjian Wu, Yunsheng Wu, Ling Shao

The search space is dynamically pruned every a few epochs to update this distribution, and the optimal neural architecture is obtained when there is only one structure remained.

Neural Architecture Search

Multinomial Distribution Learning for Effective Neural Architecture Search

1 code implementation ICCV 2019 Xiawu Zheng, Rongrong Ji, Lang Tang, Baochang Zhang, Jianzhuang Liu, Qi Tian

Therefore, NAS can be transformed to a multinomial distribution learning problem, i. e., the distribution is optimized to have a high expectation of the performance.

Neural Architecture Search

Towards Optimal Structured CNN Pruning via Generative Adversarial Learning

1 code implementation CVPR 2019 Shaohui Lin, Rongrong Ji, Chenqian Yan, Baochang Zhang, Liujuan Cao, Qixiang Ye, Feiyue Huang, David Doermann

In this paper, we propose an effective structured pruning approach that jointly prunes filters as well as other structures in an end-to-end manner.

Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network

no code implementations3 Mar 2019 Xiaolong Jiang, Zehao Xiao, Baochang Zhang, Xian-Tong Zhen, Xian-Bin Cao, David Doermann, Ling Shao

In this paper, we propose a trellis encoder-decoder network (TEDnet) for crowd counting, which focuses on generating high-quality density estimation maps.

14 Crowd Counting +1

Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression

1 code implementation CVPR 2019 Yuchao Li, Shaohui Lin, Baochang Zhang, Jianzhuang Liu, David Doermann, Yongjian Wu, Feiyue Huang, Rongrong Ji

The relationship between the input feature maps and 2D kernels is revealed in a theoretical framework, based on which a kernel sparsity and entropy (KSE) indicator is proposed to quantitate the feature map importance in a feature-agnostic manner to guide model compression.

Model Compression

Projection Convolutional Neural Networks for 1-bit CNNs via Discrete Back Propagation

no code implementations30 Nov 2018 Jiaxin Gu, Ce Li, Baochang Zhang, Jungong Han, Xian-Bin Cao, Jianzhuang Liu, David Doermann

The advancement of deep convolutional neural networks (DCNNs) has driven significant improvement in the accuracy of recognition systems for many computer vision tasks.

Object detection and tracking benchmark in industry based on improved correlation filter

no code implementations11 Jun 2018 Shangzhen Luan, Yan Li, Xiaodi Wang, Baochang Zhang

Real-time object detection and tracking have shown to be the basis of intelligent production for industrial 4. 0 applications.

Real-Time Object Detection

Modulated Convolutional Networks

no code implementations CVPR 2018 Xiaodi Wang, Baochang Zhang, Ce Li, Rongrong Ji, Jungong Han, Xian-Bin Cao, Jianzhuang Liu

In this paper, we propose new Modulated Convolutional Networks (MCNs) to improve the portability of CNNs via binarized filters.

Memory Attention Networks for Skeleton-based Action Recognition

1 code implementation23 Apr 2018 Chunyu Xie, Ce Li, Baochang Zhang, Chen Chen, Jungong Han, Changqing Zou, Jianzhuang Liu

Specifically, the TARM is deployed in a residual learning module that employs a novel attention learning network to recalibrate the temporal attention of frames in a skeleton sequence.

Action Recognition Skeleton Based Action Recognition

The Structure Transfer Machine Theory and Applications

1 code implementation1 Apr 2018 Baochang Zhang, Lian Zhuo, Ze Wang, Jungong Han, Xian-Tong Zhen

Representation learning is a fundamental but challenging problem, especially when the distribution of data is unknown.

Image Classification Object Tracking +1

Latent Constrained Correlation Filter

no code implementations11 Nov 2017 Baochang Zhang, Shangzhen Luan, Chen Chen, Jungong Han, Wei Wang, Alessandro Perina, Ling Shao

In this paper, we introduce an intermediate step -- solution sampling -- after the data sampling step to form a subspace, in which an optimal solution can be estimated.

Object Recognition Object Tracking

Manifold Constrained Low-Rank Decomposition

no code implementations6 Aug 2017 Chen Chen, Baochang Zhang, Alessio Del Bue, Vittorio Murino

Low-rank decomposition (LRD) is a state-of-the-art method for visual data reconstruction and modelling.

Cross-Modality Binary Code Learning via Fusion Similarity Hashing

no code implementations CVPR 2017 Hong Liu, Rongrong Ji, Yongjian Wu, Feiyue Huang, Baochang Zhang

In this paper, we propose a hashing scheme, termed Fusion Similarity Hashing (FSH), which explicitly embeds the graph-based fusion similarity across modalities into a common Hamming space.

Gabor Convolutional Networks

no code implementations3 May 2017 Shangzhen Luan, Baochang Zhang, Chen Chen, Xian-Bin Cao, Jungong Han, Jianzhuang Liu

Steerable properties dominate the design of traditional filters, e. g., Gabor filters, and endow features the capability of dealing with spatial transformations.

Self-learning Scene-specific Pedestrian Detectors using a Progressive Latent Model

no code implementations CVPR 2017 Qixiang Ye, Tianliang Zhang, Qiang Qiu, Baochang Zhang, Jie Chen, Guillermo Sapiro

In this paper, a self-learning approach is proposed towards solving scene-specific pedestrian detection problem without any human' annotation involved.

Frame Object Discovery +4

Latent Constrained Correlation Filters for Object Localization

no code implementations7 Jun 2016 Shangzhen Luan, Baochang Zhang, Jungong Han, Chen Chen, Ling Shao, Alessandro Perina, Linlin Shen

There is a neglected fact in the traditional machine learning methods that the data sampling can actually lead to the solution sampling.

Object Localization

Boosting-like Deep Learning For Pedestrian Detection

no code implementations26 May 2015 Lei Wang, Baochang Zhang

This paper proposes boosting-like deep learning (BDL) framework for pedestrian detection.

Pedestrian Detection

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