Search Results for author: Jian Sun

Found 184 papers, 84 papers with code

Relieving Long-tailed Instance Segmentation via Pairwise Class Balance

no code implementations8 Jan 2022 Yin-Yin He, Peizhen Zhang, Xiu-Shen Wei, Xiangyu Zhang, Jian Sun

In this paper, we explore to excavate the confusion matrix, which carries the fine-grained misclassification details, to relieve the pairwise biases, generalizing the coarse one.

Instance Segmentation Semantic Segmentation

Learning to Select the Next Reasonable Mention for Entity Linking

no code implementations8 Dec 2021 Jian Sun, Yu Zhou, Chengqing Zong

To address the problem, we propose a novel model, called DyMen, to dynamically adjust the subsequent linking target based on the previously linked entities via reinforcement learning, enabling the model to select a link target that can fully use previously linked information.

Entity Linking Knowledge Graphs

Dynamic Grained Encoder for Vision Transformers

1 code implementation NeurIPS 2021 Lin Song, Songyang Zhang, Songtao Liu, Zeming Li, Xuming He, Hongbin Sun, Jian Sun, Nanning Zheng

Specifically, we propose a Dynamic Grained Encoder for vision transformers, which can adaptively assign a suitable number of queries to each spatial region.

Image Classification Language Modelling +1

Adversarial Reweighting for Partial Domain Adaptation

1 code implementation NeurIPS 2021 Xiang Gu, Xi Yu, Yan Yang, Jian Sun, Zongben Xu

To tackle the challenge of negative domain transfer, we propose a novel Adversarial Reweighting (AR) approach that adversarially learns the weights of source domain data to align the source and target domain distributions, and the transferable deep recognition network is learned on the reweighted source domain data.

Partial Domain Adaptation

Spherical Motion Dynamics: Learning Dynamics of Normalized Neural Network using SGD and Weight Decay

no code implementations NeurIPS 2021 Ruosi Wan, Zhanxing Zhu, Xiangyu Zhang, Jian Sun

Specifically, 1) we introduce the assumptions that can lead to equilibrium state in SMD, and prove equilibrium can be reached in a linear rate regime under given assumptions; 2) we propose ``angular update" as a substitute for effective learning rate to depict the state of SMD, and derive the theoretical value of angular update in equilibrium state; 3) we verify our assumptions and theoretical results on various large-scale computer vision tasks including ImageNet and MSCOCO with standard settings.

XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks

1 code implementation21 Nov 2021 Jian Sun, Ali Pourramezan Fard, Mohammad H. Mahoor

This paper proposes a new class of Fully Connected (FC) Layers by xnorizing the linear projector outside or inside the Dynamic Routing within the CapsFC layer.

Ranked #10 on Image Classification on MNIST (Accuracy metric)

Binarization Image Classification

SDCUP: Schema Dependency-Enhanced Curriculum Pre-Training for Table Semantic Parsing

no code implementations18 Nov 2021 Bowen Qin, Lihan Wang, Binyuan Hui, Ruiying Geng, Zheng Cao, Min Yang, Jian Sun, Yongbin Li

Recently pre-training models have significantly improved the performance of various NLP tasks by leveraging large-scale text corpora to improve the contextual representation ability of the neural network.

Curriculum Learning Language Modelling +2

Distributed stochastic proximal algorithm with random reshuffling for non-smooth finite-sum optimization

no code implementations6 Nov 2021 Xia Jiang, Xianlin Zeng, Jian Sun, Jie Chen, Lihua Xie

We prove that local variable estimates generated by the proposed algorithm achieve consensus and are attracted to a neighborhood of the optimal solution in expectation with an $\mathcal{O}(\frac{1}{T}+\frac{1}{\sqrt{T}})$ convergence rate.

Path-Enhanced Multi-Relational Question Answering with Knowledge Graph Embeddings

no code implementations29 Oct 2021 Guanglin Niu, Yang Li, Chengguang Tang, Zhongkai Hu, Shibin Yang, Peng Li, Chengyu Wang, Hao Wang, Jian Sun

The multi-relational Knowledge Base Question Answering (KBQA) system performs multi-hop reasoning over the knowledge graph (KG) to achieve the answer.

Knowledge Base Question Answering Knowledge Graph Embedding +1

Data-driven Control of Dynamic Event-triggered Systems with Delays

no code implementations25 Oct 2021 Xin Wang, Jian Sun, Julian Berberich, Gang Wang, Frank Allgower, Jie Chen

Data-based representations for stochastic linear systems with a known or an unknown system input matrix are first developed, along with a novel class of dynamic triggering schemes for sampled-data systems with time delays.

Data-Driven Resilient Predictive Control under Denial-of-Service

no code implementations25 Oct 2021 Wenjie Liu, Jian Sun, Gang Wang, Francesco Bullo, Jie Chen

Finally, a numerical example is given to validate the effectiveness of the proposed control method.

Partial to Whole Knowledge Distillation: Progressive Distilling Decomposed Knowledge Boosts Student Better

no code implementations26 Sep 2021 Xuanyang Zhang, Xiangyu Zhang, Jian Sun

Knowledge distillation field delicately designs various types of knowledge to shrink the performance gap between compact student and large-scale teacher.

Knowledge Distillation

DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings

1 code implementation EMNLP 2021 Che Liu, Rui Wang, Jinghua Liu, Jian Sun, Fei Huang, Luo Si

Learning sentence embeddings from dialogues has drawn increasing attention due to its low annotation cost and high domain adaptability.

Contrastive Learning Semantic Textual Similarity +1

LGD: Label-guided Self-distillation for Object Detection

no code implementations23 Sep 2021 Peizhen Zhang, Zijian Kang, Tong Yang, Xiangyu Zhang, Nanning Zheng, Jian Sun

It boosts much stronger detectors like FCOS with ResNeXt-101 DCN v2 under 2x multi-scale training from 46. 1% to 47. 9% (+ 1. 8%).

Instance Segmentation Object Detection +2

Anchor DETR: Query Design for Transformer-Based Object Detection

2 code implementations15 Sep 2021 Yingming Wang, Xiangyu Zhang, Tong Yang, Jian Sun

Thanks to the query design and the attention variant, the proposed detector that we called Anchor DETR, can achieve better performance and run faster than the DETR with 10$\times$ fewer training epochs.

Object Detection

Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision

1 code implementation17 Aug 2021 Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, Yukang Chen, Lu Qi, LiWei Wang, Zeming Li, Jian Sun, Jiaya Jia

In particular, Panoptic FCN encodes each object instance or stuff category with the proposed kernel generator and produces the prediction by convolving the high-resolution feature directly.

Panoptic Segmentation Weakly-supervised panoptic segmentation

Learning Canonical View Representation for 3D Shape Recognition with Arbitrary Views

1 code implementation ICCV 2021 Xin Wei, Yifei Gong, Fudong Wang, Xing Sun, Jian Sun

In this way, each 3D shape with arbitrary views is represented by a fixed number of canonical view features, which are further aggregated to generate a rich and robust 3D shape representation for shape recognition.

3D Shape Recognition 3D Shape Representation

A Unified Hyper-GAN Model for Unpaired Multi-contrast MR Image Translation

no code implementations26 Jul 2021 Heran Yang, Jian Sun, Liwei Yang, Zongben Xu

Hyper-GAN consists of a pair of hyper-encoder and hyper-decoder to first map from the source contrast to a common feature space, and then further map to the target contrast image.

Translation

YOLOX: Exceeding YOLO Series in 2021

15 code implementations18 Jul 2021 Zheng Ge, Songtao Liu, Feng Wang, Zeming Li, Jian Sun

In this report, we present some experienced improvements to YOLO series, forming a new high-performance detector -- YOLOX.

Autonomous Driving Object Detection

Ill-posed Surface Emissivity Retrieval from Multi-Geometry Hyperspectral Images using a Hybrid Deep Neural Network

no code implementations9 Jul 2021 Fangcao Xu, Jian Sun, Guido Cervone, Mark Salvador

Atmospheric correction errors can significantly alter the spectral signature of the observations, and lead to invalid classifications or target detection.

Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking

no code implementations1 Jun 2021 Yinpei Dai, Hangyu Li, Yongbin Li, Jian Sun, Fei Huang, Luo Si, Xiaodan Zhu

Existing dialog state tracking (DST) models are trained with dialog data in a random order, neglecting rich structural information in a dataset.

 Ranked #1 on Multi-domain Dialogue State Tracking on MULTIWOZ 2.1 (using extra training data)

Curriculum Learning Multi-domain Dialogue State Tracking

ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging

2 code implementations22 May 2021 Zhen Liu, Wenjie Lin, Xinpeng Li, Qing Rao, Ting Jiang, Mingyan Han, Haoqiang Fan, Jian Sun, Shuaicheng Liu

In this paper, we present an attention-guided deformable convolutional network for hand-held multi-frame high dynamic range (HDR) imaging, namely ADNet.

Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion

1 code implementation27 Apr 2021 Guanglin Niu, Yang Li, Chengguang Tang, Ruiying Geng, Jian Dai, Qiao Liu, Hao Wang, Jian Sun, Fei Huang, Luo Si

Moreover, modeling and inferring complex relations of one-to-many (1-N), many-to-one (N-1), and many-to-many (N-N) by previous knowledge graph completion approaches requires high model complexity and a large amount of training instances.

Few-Shot Learning Knowledge Graph Completion +1

Points as Queries: Weakly Semi-supervised Object Detection by Points

no code implementations CVPR 2021 Liangyu Chen, Tong Yang, Xiangyu Zhang, Wei zhang, Jian Sun

We propose a novel point annotated setting for the weakly semi-supervised object detection task, in which the dataset comprises small fully annotated images and large weakly annotated images by points.

Object Detection Semi-Supervised Object Detection

Learning to Jointly Deblur, Demosaick and Denoise Raw Images

no code implementations13 Apr 2021 Thomas Eboli, Jian Sun, Jean Ponce

We address the problem of non-blind deblurring and demosaicking of noisy raw images.

Deblurring Demosaicking +1

OTA: Optimal Transport Assignment for Object Detection

1 code implementation CVPR 2021 Zheng Ge, Songtao Liu, Zeming Li, Osamu Yoshie, Jian Sun

Recent advances in label assignment in object detection mainly seek to independently define positive/negative training samples for each ground-truth (gt) object.

Object Detection

Resilient Control under Quantization and Denial-of-Service: Co-designing a Deadbeat Controller and Transmission Protocol

no code implementations22 Mar 2021 Wenjie Liu, Jian Sun, Gang Wang, Francesco Bullo, Jie Chen

When both input and output channels are subject to DoS attacks and quantization, the proposed structure is shown able to decouple the encoding schemes for input, output, and estimated output signals.

Quantization

You Only Look One-level Feature

3 code implementations CVPR 2021 Qiang Chen, Yingming Wang, Tong Yang, Xiangyu Zhang, Jian Cheng, Jian Sun

From the perspective of optimization, we introduce an alternative way to address the problem instead of adopting the complex feature pyramids - {\em utilizing only one-level feature for detection}.

Object Detection

Training Networks in Null Space of Feature Covariance for Continual Learning

1 code implementation CVPR 2021 Shipeng Wang, Xiaorong Li, Jian Sun, Zongben Xu

To balance plasticity and stability of network in continual learning, in this paper, we propose a novel network training algorithm called Adam-NSCL, which sequentially optimizes network parameters in the null space of previous tasks.

Continual Learning

Improving Text-to-SQL with Schema Dependency Learning

no code implementations7 Mar 2021 Binyuan Hui, Xiang Shi, Ruiying Geng, Binhua Li, Yongbin Li, Jian Sun, Xiaodan Zhu

In this paper, we present the Schema Dependency guided multi-task Text-to-SQL model (SDSQL) to guide the network to effectively capture the interactions between questions and schemas.

Text-To-Sql

FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation

3 code implementations CVPR 2021 Yisheng He, Haibin Huang, Haoqiang Fan, Qifeng Chen, Jian Sun

Moreover, at the output representation stage, we designed a simple but effective 3D keypoints selection algorithm considering the texture and geometry information of objects, which simplifies keypoint localization for precise pose estimation.

6D Pose Estimation Representation Learning

Using Long Short-Term Memory (LSTM) and Internet of Things (IoT) for localized surface temperature forecasting in an urban environment

no code implementations4 Feb 2021 Manzhu Yu, Fangcao Xu, Weiming Hu, Jian Sun, Guido Cervone

Meanwhile, by using IoT observations, the spatial resolution of air temperature predictions is significantly improved.

Neural Architecture Search with Random Labels

1 code implementation CVPR 2021 Xuanyang Zhang, Pengfei Hou, Xiangyu Zhang, Jian Sun

In this paper, we investigate a new variant of neural architecture search (NAS) paradigm -- searching with random labels (RLNAS).

Neural Architecture Search

Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learning

1 code implementation19 Jan 2021 Zeming Li, Songtao Liu, Jian Sun

The teacher's weight is a momentum update of the student, and the teacher's BN statistics is a momentum update of those in history.

Self-Supervised Learning

RepVGG: Making VGG-style ConvNets Great Again

14 code implementations CVPR 2021 Xiaohan Ding, Xiangyu Zhang, Ningning Ma, Jungong Han, Guiguang Ding, Jian Sun

We present a simple but powerful architecture of convolutional neural network, which has a VGG-like inference-time body composed of nothing but a stack of 3x3 convolution and ReLU, while the training-time model has a multi-branch topology.

Image Classification Semantic Segmentation

Domain-Free Adversarial Splitting for Domain Generalization

no code implementations1 Jan 2021 Xiang Gu, Jiasun Feng, Jian Sun, Zongben Xu

In this framework, we model the domain generalization as a learning problem that enforces the learner to be able to generalize well for any train/val subsets splitting of the training dataset.

Domain Generalization Meta-Learning

Implicit Feature Pyramid Network for Object Detection

no code implementations25 Dec 2020 Tiancai Wang, Xiangyu Zhang, Jian Sun

In this paper, we present an implicit feature pyramid network (i-FPN) for object detection.

Object Detection

Efficient Human Pose Estimation by Learning Deeply Aggregated Representations

no code implementations13 Dec 2020 Zhengxiong Luo, Zhicheng Wang, Yuanhao Cai, GuanAn Wang, Yan Huang, Liang Wang, Erjin Zhou, Tieniu Tan, Jian Sun

Instead, we focus on exploiting multi-scale information from layers with different receptive-field sizes and then making full of use this information by improving the fusion method.

Pose Estimation

Fine-Grained Dynamic Head for Object Detection

1 code implementation NeurIPS 2020 Lin Song, Yanwei Li, Zhengkai Jiang, Zeming Li, Hongbin Sun, Jian Sun, Nanning Zheng

To this end, we propose a fine-grained dynamic head to conditionally select a pixel-level combination of FPN features from different scales for each instance, which further releases the ability of multi-scale feature representation.

Object Detection

End-to-End Object Detection with Fully Convolutional Network

1 code implementation CVPR 2021 JianFeng Wang, Lin Song, Zeming Li, Hongbin Sun, Jian Sun, Nanning Zheng

Mainstream object detectors based on the fully convolutional network has achieved impressive performance.

Object Detection

Fully Convolutional Networks for Panoptic Segmentation

5 code implementations CVPR 2021 Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, LiWei Wang, Zeming Li, Jian Sun, Jiaya Jia

In this paper, we present a conceptually simple, strong, and efficient framework for panoptic segmentation, called Panoptic FCN.

 Ranked #1 on Panoptic Segmentation on Cityscapes val (PQst metric)

Panoptic Segmentation

Dual Attention Network for Cross-lingual Entity Alignment

no code implementations COLING 2020 Jian Sun, Yu Zhou, Chengqing Zong

The hierarchical attention adaptively aggregates the low-hierarchy and the high-hierarchy information, which is beneficial to balance the neighborhood information of counterpart entities and distinguish non-counterpart entities with similar structures.

Entity Alignment Graph Attention +1

Decentralized TD Tracking with Linear Function Approximation and its Finite-Time Analysis

no code implementations NeurIPS 2020 Gang Wang, Songtao Lu, Georgios Giannakis, Gerald Tesauro, Jian Sun

The present contribution deals with decentralized policy evaluation in multi-agent Markov decision processes using temporal-difference (TD) methods with linear function approximation for scalability.

UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning

1 code implementation CVPR 2021 Kunming Luo, Chuan Wang, Shuaicheng Liu, Haoqiang Fan, Jue Wang, Jian Sun

By integrating these two components together, our method achieves the best performance for unsupervised optical flow learning on multiple leading benchmarks, including MPI-SIntel, KITTI 2012 and KITTI 2015.

Optical Flow Estimation

Self-EMD: Self-Supervised Object Detection without ImageNet

no code implementations27 Nov 2020 Songtao Liu, Zeming Li, Jian Sun

Our Faster R-CNN (ResNet50-FPN) baseline achieves 39. 8% mAP on COCO, which is on par with the state of the art self-supervised methods pre-trained on ImageNet.

Object Detection Representation Learning

Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysis

no code implementations ECCV 2020 Ruixuan Yu, Xin Wei, Federico Tombari, Jian Sun

In this work, we propose a novel deep network for point clouds by incorporating positional information of points as inputs while yielding rotation-invariance.

Joint COCO and Mapillary Workshop at ICCV 2019: COCO Instance Segmentation Challenge Track

no code implementations6 Oct 2020 Zeming Li, Yuchen Ma, Yukang Chen, Xiangyu Zhang, Jian Sun

In this report, we present our object detection/instance segmentation system, MegDetV2, which works in a two-pass fashion, first to detect instances then to obtain segmentation.

Instance Segmentation Object Detection +1

EqCo: Equivalent Rules for Self-supervised Contrastive Learning

1 code implementation5 Oct 2020 Benjin Zhu, Junqiang Huang, Zeming Li, Xiangyu Zhang, Jian Sun

In this paper, we propose a method, named EqCo (Equivalent Rules for Contrastive Learning), to make self-supervised learning irrelevant to the number of negative samples in InfoNCE-based contrastive learning frameworks.

Contrastive Learning Self-Supervised Learning

Activate or Not: Learning Customized Activation

3 code implementations CVPR 2021 Ningning Ma, Xiangyu Zhang, Ming Liu, Jian Sun

We present a simple, effective, and general activation function we term ACON which learns to activate the neurons or not.

Object Detection Semantic Segmentation

Multi-Frequency Multi-Scenario Millimeter Wave MIMO Channel Measurements and Modeling for B5G Wireless Communication Systems

no code implementations28 Jul 2020 Jie Huang, Cheng-Xiang Wang, Hengtai Chang, Jian Sun, Xiqi Gao

Millimeter wave (mmWave) bands have been utilized for the fifth generation (5G) communication systems and will no doubt continue to be deployed for beyond 5G (B5G).

A Non-Stationary VVLC MIMO Channel Model for Street Corner Scenarios

no code implementations28 Jul 2020 Qingshan Chen, Cheng-Xiang Wang, Jian Sun, Wensheng Zhang, Qiuming Zhu

The study of the underlying VLC channel is the basis for designing the VLC communication system.

A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges

no code implementations26 Jul 2020 Bin Fu, Yunqi Qiu, Chengguang Tang, Yang Li, Haiyang Yu, Jian Sun

Question Answering (QA) over Knowledge Base (KB) aims to automatically answer natural language questions via well-structured relation information between entities stored in knowledge bases.

Information Retrieval Question Answering +1

WeightNet: Revisiting the Design Space of Weight Networks

2 code implementations ECCV 2020 Ningning Ma, Xiangyu Zhang, Jiawei Huang, Jian Sun

WeightNet is easy and memory-conserving to train, on the kernel space instead of the feature space.

Funnel Activation for Visual Recognition

7 code implementations ECCV 2020 Ningning Ma, Xiangyu Zhang, Jian Sun

We present a conceptually simple but effective funnel activation for image recognition tasks, called Funnel activation (FReLU), that extends ReLU and PReLU to a 2D activation by adding a negligible overhead of spatial condition.

Scene Generation Semantic Segmentation

BorderDet: Border Feature for Dense Object Detection

2 code implementations ECCV 2020 Han Qiu, Yuchen Ma, Zeming Li, Songtao Liu, Jian Sun

In this paper, We propose a simple and efficient operator called Border-Align to extract "border features" from the extreme point of the border to enhance the point feature.

Dense Object Detection

Learning from Manipulable Signals

no code implementations17 Jul 2020 Mehmet Ekmekci, Leandro Gorno, Lucas Maestri, Jian Sun, Dong Wei

The principal learns about the agent's type from a noisy performance measure, which can be manipulated by the agent via a costly and hidden action.

AutoAssign: Differentiable Label Assignment for Dense Object Detection

1 code implementation7 Jul 2020 Benjin Zhu, Jian-Feng Wang, Zhengkai Jiang, Fuhang Zong, Songtao Liu, Zeming Li, Jian Sun

During training, to both satisfy the prior distribution of data and adapt to category characteristics, we present Center Weighting to adjust the category-specific prior distributions.

Dense Object Detection

LabelEnc: A New Intermediate Supervision Method for Object Detection

1 code implementation ECCV 2020 Miao Hao, Yitao Liu, Xiangyu Zhang, Jian Sun

In this paper we propose a new intermediate supervision method, named LabelEnc, to boost the training of object detection systems.

Object Detection

End-to-end Interpretable Learning of Non-blind Image Deblurring

1 code implementation ECCV 2020 Thomas Eboli, Jian Sun, Jean Ponce

Non-blind image deblurring is typically formulated as a linear least-squares problem regularized by natural priors on the corresponding sharp picture's gradients, which can be solved, for example, using a half-quadratic splitting method with Richardson fixed-point iterations for its least-squares updates and a proximal operator for the auxiliary variable updates.

Blind Image Deblurring Image Deblurring

Structured and Localized Image Restoration

no code implementations16 Jun 2020 Thomas Eboli, Alex Nowak-Vila, Jian Sun, Francis Bach, Jean Ponce, Alessandro Rudi

We present a novel approach to image restoration that leverages ideas from localized structured prediction and non-linear multi-task learning.

Image Restoration Multi-Task Learning +1

Online Reinforcement Learning Control by Direct Heuristic Dynamic Programming: from Time-Driven to Event-Driven

no code implementations16 Jun 2020 Qingtao Zhao, Jennie Si, Jian Sun

In this paper time-driven learning refers to the machine learning method that updates parameters in a prediction model continuously as new data arrives.

Spherical Motion Dynamics: Learning Dynamics of Neural Network with Normalization, Weight Decay, and SGD

no code implementations15 Jun 2020 Ruosi Wan, Zhanxing Zhu, Xiangyu Zhang, Jian Sun

In this work, we comprehensively reveal the learning dynamics of neural network with normalization, weight decay (WD), and SGD (with momentum), named as Spherical Motion Dynamics (SMD).

Joint Multi-Dimension Pruning via Numerical Gradient Update

no code implementations18 May 2020 Zechun Liu, Xiangyu Zhang, Zhiqiang Shen, Zhe Li, Yichen Wei, Kwang-Ting Cheng, Jian Sun

To tackle these three naturally different dimensions, we proposed a general framework by defining pruning as seeking the best pruning vector (i. e., the numerical value of layer-wise channel number, spacial size, depth) and construct a unique mapping from the pruning vector to the pruned network structures.

A Survey on Dialog Management: Recent Advances and Challenges

no code implementations5 May 2020 Yinpei Dai, Huihua Yu, Yixuan Jiang, Chengguang Tang, Yongbin Li, Jian Sun

Dialog management (DM) is a crucial component in a task-oriented dialog system.

Angle-based Search Space Shrinking for Neural Architecture Search

1 code implementation ECCV 2020 Yiming Hu, Yuding Liang, Zichao Guo, Ruosi Wan, Xiangyu Zhang, Yichen Wei, Qingyi Gu, Jian Sun

Comprehensive experiments show that ABS can dramatically enhance existing NAS approaches by providing a promising shrunk search space.

Neural Architecture Search

Dynamic Scale Training for Object Detection

4 code implementations26 Apr 2020 Yukang Chen, Peizhen Zhang, Zeming Li, Yanwei Li, Xiangyu Zhang, Lu Qi, Jian Sun, Jiaya Jia

We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection.

Instance Segmentation Object Detection +1

Attentive Normalization for Conditional Image Generation

1 code implementation CVPR 2020 Yi Wang, Ying-Cong Chen, Xiangyu Zhang, Jian Sun, Jiaya Jia

Traditional convolution-based generative adversarial networks synthesize images based on hierarchical local operations, where long-range dependency relation is implicitly modeled with a Markov chain.

Conditional Image Generation Semantic correspondence +2

Learning Human-Object Interaction Detection using Interaction Points

1 code implementation CVPR 2020 Tiancai Wang, Tong Yang, Martin Danelljan, Fahad Shahbaz Khan, Xiangyu Zhang, Jian Sun

Human-object interaction (HOI) detection strives to localize both the human and an object as well as the identification of complex interactions between them.

Human-Object Interaction Detection Keypoint Detection +1

Dynamic Region-Aware Convolution

no code implementations CVPR 2021 Jin Chen, Xijun Wang, Zichao Guo, Xiangyu Zhang, Jian Sun

More gracefully, our DRConv transfers the increasing channel-wise filters to spatial dimension with learnable instructor, which not only improve representation ability of convolution, but also maintains computational cost and the translation-invariance as standard convolution dose.

Face Recognition General Classification +1

Learning Dynamic Routing for Semantic Segmentation

no code implementations CVPR 2020 Yanwei Li, Lin Song, Yukang Chen, Zeming Li, Xiangyu Zhang, Xingang Wang, Jian Sun

To demonstrate the superiority of the dynamic property, we compare with several static architectures, which can be modeled as special cases in the routing space.

Semantic Segmentation

Detection in Crowded Scenes: One Proposal, Multiple Predictions

3 code implementations CVPR 2020 Xuangeng Chu, Anlin Zheng, Xiangyu Zhang, Jian Sun

We propose a simple yet effective proposal-based object detector, aiming at detecting highly-overlapped instances in crowded scenes.

Object Detection Pedestrian Detection

High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification

2 code implementations CVPR 2020 Guan'an Wang, Shuo Yang, Huanyu Liu, Zhicheng Wang, Yang Yang, Shuliang Wang, Gang Yu, Erjin Zhou, Jian Sun

When aligning two groups of local features from two images, we view it as a graph matching problem and propose a cross-graph embedded-alignment (CGEA) layer to jointly learn and embed topology information to local features, and straightly predict similarity score.

Graph Matching Person Re-Identification

PointINS: Point-based Instance Segmentation

no code implementations13 Mar 2020 Lu Qi, Yi Wang, Yukang Chen, Yingcong Chen, Xiangyu Zhang, Jian Sun, Jiaya Jia

In this paper, we explore the mask representation in instance segmentation with Point-of-Interest (PoI) features.

Instance Segmentation Object Detection +2

Learning Delicate Local Representations for Multi-Person Pose Estimation

3 code implementations ECCV 2020 Yuanhao Cai, Zhicheng Wang, Zhengxiong Luo, Binyi Yin, Angang Du, Haoqian Wang, Xiangyu Zhang, Xinyu Zhou, Erjin Zhou, Jian Sun

To tackle this problem, we propose an efficient attention mechanism - Pose Refine Machine (PRM) to make a trade-off between local and global representations in output features and further refine the keypoint locations.

Multi-Person Pose Estimation

Gauss-Newton Unrolled Neural Networks and Data-driven Priors for Regularized PSSE with Robustness

no code implementations3 Mar 2020 Qiuling Yang, Alireza Sadeghi, Gang Wang, Georgios B. Giannakis, Jian Sun

Numerical tests using real load data on the IEEE $118$-bus benchmark system showcase the improved estimation and robustness performance of the proposed scheme compared with several state-of-the-art alternatives.

Image Denoising

A Big Data Enabled Channel Model for 5G Wireless Communication Systems

no code implementations28 Feb 2020 Jie Huang, Cheng-Xiang Wang, Lu Bai, Jian Sun, Yang Yang, Jie Li, Olav Tirkkonen, Ming-Tuo Zhou

This paper investigates various applications of big data analytics, especially machine learning algorithms in wireless communications and channel modeling.

Isotropic All-electric Spin analyzer based on a quantum ring with spin-orbit coupling

no code implementations4 Feb 2020 Shenglin Peng, Wenchen Luo, Jian Sun, Ai-Min Guo, Fangping Ouyang, Tapash Chakraborty

Here we propose an isotropic all electrical spin analyzer in a quantum ring with spin-orbit coupling by analytically and numerically modeling how the charge transmission rates depend on the polarization of the incident spin.

Mesoscale and Nanoscale Physics

Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization

1 code implementation ICLR 2020 Junjie Yan, Ruosi Wan, Xiangyu Zhang, Wei zhang, Yichen Wei, Jian Sun

Therefore many modified normalization techniques have been proposed, which either fail to restore the performance of BN completely, or have to introduce additional nonlinear operations in inference procedure and increase huge consumption.

Learning Neural Surrogate Model for Warm-Starting Bayesian Optimization

no code implementations ICLR 2020 Haotian Zhang, Jian Sun, Zongben Xu

Bayesian optimization is an effective tool to optimize black-box functions and popular for hyper-parameter tuning in machine learning.

Neural Diffusion Distance for Image Segmentation

no code implementations NeurIPS 2019 Jian Sun, Zongben Xu

To compute high-resolution diffusion distance or segmentation mask, we design an up-sampling strategy by feature-attentional interpolation which can be learned when training spec-diff-net.

Weakly-Supervised Semantic Segmentation

Conductor Galloping Prediction on Imbalanced Datasets: SVM with Smart Sampling

no code implementations9 Nov 2019 Kui Wang, Jian Sun, Chenye Wu, Yang Yu

Conductor galloping is the high-amplitude, low-frequency oscillation of overhead power lines due to wind.

A Statistical Learning Approach to Reactive Power Control in Distribution Systems

no code implementations25 Oct 2019 Qiuling Yang, Alireza Sadeghi, Gang Wang, Georgios B. Giannakis, Jian Sun

Taking a statistical learning viewpoint, the input-output relationship between each grid state and the corresponding optimal reactive power control is parameterized in the present work by a deep neural network, whose unknown weights are learned offline by minimizing the power loss over a number of historical and simulated training pairs.

VAENAS: Sampling Matters in Neural Architecture Search

no code implementations25 Sep 2019 Shizheng Qin, Yichen Zhu, Pengfei Hou, Xiangyu Zhang, Wenqiang Zhang, Jian Sun

In this paper, we propose a learnable sampling module based on variational auto-encoder (VAE) for neural architecture search (NAS), named as VAENAS, which can be easily embedded into existing weight sharing NAS framework, e. g., one-shot approach and gradient-based approach, and significantly improve the performance of searching results.

Neural Architecture Search

Resizable Neural Networks

no code implementations25 Sep 2019 Yichen Zhu, Xiangyu Zhang, Tong Yang, Jian Sun

We introduce the adaptive resizable networks as dynamic networks, which further improve the performance with less computational cost via data-dependent inference.

Data Augmentation Neural Architecture Search

Disentangled Image Matting

no code implementations ICCV 2019 Shaofan Cai, Xiaoshuai Zhang, Haoqiang Fan, Haibin Huang, Jiangyu Liu, Jiaming Liu, Jiaying Liu, Jue Wang, Jian Sun

Most previous image matting methods require a roughly-specificed trimap as input, and estimate fractional alpha values for all pixels that are in the unknown region of the trimap.

Image Matting Matting

HRGE-Net: Hierarchical Relational Graph Embedding Network for Multi-view 3D Shape Recognition

no code implementations27 Aug 2019 Xin Wei, Ruixuan Yu, Jian Sun

We construct a relational graph with multi-view images as nodes, and design relational graph embedding by modeling pairwise and neighboring relations among views.

3D Shape Classification 3D Shape Recognition +1

DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation

2 code implementations CVPR 2019 Hanchao Li, Pengfei Xiong, Haoqiang Fan, Jian Sun

This paper introduces an extremely efficient CNN architecture named DFANet for semantic segmentation under resource constraints.

Real-Time Semantic Segmentation

Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification

1 code implementation CVPR 2019 Yifan Sun, Qin Xu, Ya-Li Li, Chi Zhang, Yikang Li, Shengjin Wang, Jian Sun

The visibility awareness allows VPM to extract region-level features and compare two images with focus on their shared regions (which are visible on both images).

Person Re-Identification

ThunderNet: Towards Real-time Generic Object Detection

3 code implementations28 Mar 2019 Zheng Qin, Zeming Li, Zhaoning Zhang, Yiping Bao, Gang Yu, Yuxing Peng, Jian Sun

In this paper, we investigate the effectiveness of two-stage detectors in real-time generic detection and propose a lightweight two-stage detector named ThunderNet.

Object Detection

DetNAS: Backbone Search for Object Detection

2 code implementations NeurIPS 2019 Yukang Chen, Tong Yang, Xiangyu Zhang, Gaofeng Meng, Xinyu Xiao, Jian Sun

In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better backbones for object detection.

General Classification Image Classification +2

Meta-SR: A Magnification-Arbitrary Network for Super-Resolution

1 code implementation CVPR 2019 Xuecai Hu, Haoyuan Mu, Xiangyu Zhang, Zilei Wang, Tieniu Tan, Jian Sun

In this work, we propose a novel method called Meta-SR to firstly solve super-resolution of arbitrary scale factor (including non-integer scale factors) with a single model.

Image Super-Resolution

HyperAdam: A Learnable Task-Adaptive Adam for Network Training

2 code implementations22 Nov 2018 Shipeng Wang, Jian Sun, Zongben Xu

Deep neural networks are traditionally trained using human-designed stochastic optimization algorithms, such as SGD and Adam.

Stochastic Optimization

Rendering Portraitures from Monocular Camera and Beyond

no code implementations ECCV 2018 Xiangyu Xu, Deqing Sun, Sifei Liu, Wenqi Ren, Yu-Jin Zhang, Ming-Hsuan Yang, Jian Sun

Specifically, we first exploit Convolutional Neural Networks to estimate the relative depth and portrait segmentation maps from a single input image.

Image Matting Matting +1

Proximal Dehaze-Net: A Prior Learning-Based Deep Network for Single Image Dehazing

no code implementations ECCV 2018 Dong Yang, Jian Sun

In this paper, we propose a novel deep learning approach for single image dehazing by learning dark channel and transmission priors.

Image Dehazing Single Image Dehazing

GridFace: Face Rectification via Learning Local Homography Transformations

no code implementations ECCV 2018 Erjin Zhou, Zhimin Cao, Jian Sun

In this paper, we propose a method, called GridFace, to reduce facial geometric variations and improve the recognition performance.

Face Recognition Image Generation +1

Unified Perceptual Parsing for Scene Understanding

16 code implementations ECCV 2018 Tete Xiao, Yingcheng Liu, Bolei Zhou, Yuning Jiang, Jian Sun

In this paper, we study a new task called Unified Perceptual Parsing, which requires the machine vision systems to recognize as many visual concepts as possible from a given image.

Scene Understanding Semantic Segmentation

Learning Visually-Grounded Semantics from Contrastive Adversarial Samples

1 code implementation COLING 2018 Haoyue Shi, Jiayuan Mao, Tete Xiao, Yuning Jiang, Jian Sun

Begin with an insightful adversarial attack on VSE embeddings, we show the limitation of current frameworks and image-text datasets (e. g., MS-COCO) both quantitatively and qualitatively.

Adversarial Attack Image Captioning

CrowdHuman: A Benchmark for Detecting Human in a Crowd

1 code implementation30 Apr 2018 Shuai Shao, Zijian Zhao, Boxun Li, Tete Xiao, Gang Yu, Xiangyu Zhang, Jian Sun

There are a total of $470K$ human instances from the train and validation subsets, and $~22. 6$ persons per image, with various kinds of occlusions in the dataset.

Ranked #3 on Pedestrian Detection on Caltech (using extra training data)

Human Detection Object Detection +1

DetNet: A Backbone network for Object Detection

2 code implementations17 Apr 2018 Zeming Li, Chao Peng, Gang Yu, Xiangyu Zhang, Yangdong Deng, Jian Sun

Due to the gap between the image classification and object detection, we propose DetNet in this paper, which is a novel backbone network specifically designed for object detection.

General Classification Image Classification +3

ExFuse: Enhancing Feature Fusion for Semantic Segmentation

no code implementations ECCV 2018 Zhenli Zhang, Xiangyu Zhang, Chao Peng, Dazhi Cheng, Jian Sun

Modern semantic segmentation frameworks usually combine low-level and high-level features from pre-trained backbone convolutional models to boost performance.

Ranked #3 on Semantic Segmentation on PASCAL VOC 2012 val (using extra training data)

Semantic Segmentation

AlignedReID: Surpassing Human-Level Performance in Person Re-Identification

6 code implementations22 Nov 2017 Xuan Zhang, Hao Luo, Xing Fan, Weilai Xiang, Yixiao Sun, Qiqi Xiao, Wei Jiang, Chi Zhang, Jian Sun

In this paper, we propose a novel method called AlignedReID that extracts a global feature which is jointly learned with local features.

Person Re-Identification

Repulsion Loss: Detecting Pedestrians in a Crowd

2 code implementations CVPR 2018 Xinlong Wang, Tete Xiao, Yuning Jiang, Shuai Shao, Jian Sun, Chunhua Shen

In this paper, we first explore how a state-of-the-art pedestrian detector is harmed by crowd occlusion via experimentation, providing insights into the crowd occlusion problem.

Ranked #5 on Pedestrian Detection on Caltech (using extra training data)

Pedestrian Detection

Cascaded Pyramid Network for Multi-Person Pose Estimation

4 code implementations CVPR 2018 Yilun Chen, Zhicheng Wang, Yuxiang Peng, Zhiqiang Zhang, Gang Yu, Jian Sun

In this paper, we present a novel network structure called Cascaded Pyramid Network (CPN) which targets to relieve the problem from these "hard" keypoints.

Keypoint Detection Multi-Person Pose Estimation

Light-Head R-CNN: In Defense of Two-Stage Object Detector

5 code implementations20 Nov 2017 Zeming Li, Chao Peng, Gang Yu, Xiangyu Zhang, Yangdong Deng, Jian Sun

More importantly, simply replacing the backbone with a tiny network (e. g, Xception), our Light-Head R-CNN gets 30. 7 mmAP at 102 FPS on COCO, significantly outperforming the single-stage, fast detectors like YOLO and SSD on both speed and accuracy.

MegDet: A Large Mini-Batch Object Detector

6 code implementations CVPR 2018 Chao Peng, Tete Xiao, Zeming Li, Yuning Jiang, Xiangyu Zhang, Kai Jia, Gang Yu, Jian Sun

The improvements in recent CNN-based object detection works, from R-CNN [11], Fast/Faster R-CNN [10, 31] to recent Mask R-CNN [14] and RetinaNet [24], mainly come from new network, new framework, or novel loss design.

Object Detection

Channel Pruning for Accelerating Very Deep Neural Networks

1 code implementation ICCV 2017 Yihui He, Xiangyu Zhang, Jian Sun

In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks. Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression based channel selection and least square reconstruction.

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

21 code implementations CVPR 2018 Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, Jian Sun

We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e. g., 10-150 MFLOPs).

General Classification Image Classification +2

ADMM-Net: A Deep Learning Approach for Compressive Sensing MRI

no code implementations19 May 2017 Yan Yang, Jian Sun, Huibin Li, Zongben Xu

Due to the combination of the advantages in model-based approach and deep learning approach, the ADMM-Nets achieve state-of-the-art reconstruction accuracies with fast computational speed.

Compressive Sensing Image Reconstruction

Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network

2 code implementations CVPR 2017 Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, Jian Sun

One of recent trends [30, 31, 14] in network architec- ture design is stacking small filters (e. g., 1x1 or 3x3) in the entire network because the stacked small filters is more ef- ficient than a large kernel, given the same computational complexity.

Semantic Segmentation

Supervised Transformer Network for Efficient Face Detection

no code implementations19 Jul 2016 Dong Chen, Gang Hua, Fang Wen, Jian Sun

For real-time performance, we run the cascaded network only on regions of interests produced from a boosting cascade face detector.

Face Detection Region Proposal

R-FCN: Object Detection via Region-based Fully Convolutional Networks

44 code implementations NeurIPS 2016 Jifeng Dai, Yi Li, Kaiming He, Jian Sun

In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almost all computation shared on the entire image.

Real-Time Object Detection Translation

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

no code implementations CVPR 2016 Di Lin, Jifeng Dai, Jiaya Jia, Kaiming He, Jian Sun

Large-scale data is of crucial importance for learning semantic segmentation models, but annotating per-pixel masks is a tedious and inefficient procedure.

Semantic Segmentation

Rich Image Captioning in the Wild

no code implementations30 Mar 2016 Kenneth Tran, Xiaodong He, Lei Zhang, Jian Sun, Cornelia Carapcea, Chris Thrasher, Chris Buehler, Chris Sienkiewicz

We present an image caption system that addresses new challenges of automatically describing images in the wild.

Image Captioning

Instance-sensitive Fully Convolutional Networks

no code implementations29 Mar 2016 Jifeng Dai, Kaiming He, Yi Li, Shaoqing Ren, Jian Sun

In contrast to the previous FCN that generates one score map, our FCN is designed to compute a small set of instance-sensitive score maps, each of which is the outcome of a pixel-wise classifier of a relative position to instances.

Semantic Segmentation

Identity Mappings in Deep Residual Networks

48 code implementations16 Mar 2016 Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun

Deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors.

Image Classification

Deep Residual Learning for Image Recognition

366 code implementations CVPR 2016 Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun

Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

Image-to-Image Translation Object Detection +5

Learning Discriminative Reconstructions for Unsupervised Outlier Removal

no code implementations ICCV 2015 Yan Xia, Xudong Cao, Fang Wen, Gang Hua, Jian Sun

We study the problem of automatically removing outliers from noisy data, with application for removing outlier images from an image collection.

Dual-Feature Warping-Based Motion Model Estimation

no code implementations ICCV 2015 Shiwei Li, Lu Yuan, Jian Sun, Long Quan

Line segment is a prominent feature in artificial environments and it can supply sufficient geometrical and structural information of scenes, which not only helps guild to a correct warp in low-texture condition, but also prevents the undesired distortion induced by warping.

Image Stitching Video Stabilization

Deep Representation of Facial Geometric and Photometric Attributes for Automatic 3D Facial Expression Recognition

no code implementations10 Nov 2015 Huibin Li, Jian Sun, Dong Wang, Zongben Xu, Liming Chen

In this paper, we present a novel approach to automatic 3D Facial Expression Recognition (FER) based on deep representation of facial 3D geometric and 2D photometric attributes.

3D Facial Expression Recognition

Harmonic Extension

no code implementations22 Sep 2015 Zuoqiang Shi, Jian Sun, Minghao Tian

To tackle this problem, we propose a new method called the point integral method (PIM).

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

159 code implementations NeurIPS 2015 Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun

In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals.

Real-Time Object Detection Region Proposal

A Geodesic-Preserving Method for Image Warping

no code implementations CVPR 2015 Dongping Li, Kaiming He, Jian Sun, Kun Zhou

The image projections will turn the straight lines into curved "geodesic lines", and it is fundamentally impossible to keep all these lines straight.

Image Manipulation

Cascaded Hand Pose Regression

no code implementations CVPR 2015 Xiao Sun, Yichen Wei, Shuang Liang, Xiaoou Tang, Jian Sun

We extends the previous 2D cascaded object pose regression work [9] in two aspects so that it works better for 3D articulated objects.

3D Hand Pose Estimation

Global Refinement of Random Forest

no code implementations CVPR 2015 Shaoqing Ren, Xudong Cao, Yichen Wei, Jian Sun

The global pruning is developed to reduce the model size as well as the over-fitting risk.

Accelerating Very Deep Convolutional Networks for Classification and Detection

no code implementations26 May 2015 Xiangyu Zhang, Jianhua Zou, Kaiming He, Jian Sun

This paper aims to accelerate the test-time computation of convolutional neural networks (CNNs), especially very deep CNNs that have substantially impacted the computer vision community.

General Classification Model Compression +1

Fast Guided Filter

5 code implementations5 May 2015 Kaiming He, Jian Sun

The guided filter is a technique for edge-aware image filtering.

Object Detection Networks on Convolutional Feature Maps

no code implementations23 Apr 2015 Shaoqing Ren, Kaiming He, Ross Girshick, Xiangyu Zhang, Jian Sun

We discover that aside from deep feature maps, a deep and convolutional per-region classifier is of particular importance for object detection, whereas latest superior image classification models (such as ResNets and GoogLeNets) do not directly lead to good detection accuracy without using such a per-region classifier.

General Classification Image Classification +1

Total Variation Regularized Tensor RPCA for Background Subtraction from Compressive Measurements

no code implementations6 Mar 2015 Wenfei Cao, Yao Wang, Jian Sun, Deyu Meng, Can Yang, Andrzej Cichocki, Zongben Xu

In this paper, we propose a novel tensor-based robust PCA (TenRPCA) approach for BSCM by decomposing video frames into backgrounds with spatial-temporal correlations and foregrounds with spatio-temporal continuity in a tensor framework.

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

no code implementations ICCV 2015 Jifeng Dai, Kaiming He, Jian Sun

Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks.

Semantic Segmentation

Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal

no code implementations CVPR 2015 Jian Sun, Wenfei Cao, Zongben Xu, Jean Ponce

In this paper, we address the problem of estimating and removing non-uniform motion blur from a single blurry image.

Deblurring