Search Results for author:
Found 184 papers, 84 papers with code
Relieving Long-tailed Instance Segmentation via Pairwise Class Balance
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.
Learning to Select the Next Reasonable Mention for Entity Linking
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.
Dynamic Grained Encoder for Vision Transformers
Specifically, we propose a Dynamic Grained Encoder for vision transformers, which can adaptively assign a suitable number of queries to each spatial region.
Adversarial Reweighting for Partial Domain Adaptation
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.
Ranked #1 on
Partial Domain Adaptation
on ImageNet-Caltech
Spherical Motion Dynamics: Learning Dynamics of Normalized Neural Network using SGD and Weight Decay
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.
GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection
Pre-trained models have proved to be powerful in enhancing task-oriented dialog systems.
XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks
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)
SDCUP: Schema Dependency-Enhanced Curriculum Pre-Training for Table Semantic Parsing
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.
Distributed stochastic proximal algorithm with random reshuffling for non-smooth finite-sum optimization
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
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
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.
Instance-Conditional Knowledge Distillation for Object Detection
Knowledge distillation has shown great success in classification, however, it is still challenging for detection.
Data-Driven Resilient Predictive Control under Denial-of-Service
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
Knowledge distillation field delicately designs various types of knowledge to shrink the performance gap between compact student and large-scale teacher.
DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings
Learning sentence embeddings from dialogues has drawn increasing attention due to its low annotation cost and high domain adaptability.
LGD: Label-guided Self-distillation for Object Detection
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%).
Anchor DETR: Query Design for Transformer-Based Object Detection
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.
Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision
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
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.
Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking
Existing dialog state tracking (DST) models are trained with dialog data in a random order, neglecting rich structural information in a dataset.
Workshop on Autonomous Driving at CVPR 2021: Technical Report for Streaming Perception Challenge
In this report, we introduce our real-time 2D object detection system for the realistic autonomous driving scenario.
A Unified Hyper-GAN Model for Unpaired Multi-contrast MR Image Translation
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.
YOLOX: Exceeding YOLO Series in 2021
In this report, we present some experienced improvements to YOLO series, forming a new high-performance detector -- YOLOX.
Ranked #46 on
Object Detection
on COCO test-dev
Ill-posed Surface Emissivity Retrieval from Multi-Geometry Hyperspectral Images using a Hybrid Deep Neural Network
Atmospheric correction errors can significantly alter the spectral signature of the observations, and lead to invalid classifications or target detection.
NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results
This paper reviews the NTIRE2021 challenge on burst super-resolution.
Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking
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)
ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging
In this paper, we present an attention-guided deformable convolutional network for hand-held multi-frame high dynamic range (HDR) imaging, namely ADNet.
Generalized Few-Shot Object Detection without Forgetting
Recently few-shot object detection is widely adopted to deal with data-limited situations.
Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report
A detailed description of all models developed in the challenge is provided in this paper.
Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion
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.
Points as Queries: Weakly Semi-supervised Object Detection by Points
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.
IQDet: Instance-wise Quality Distribution Sampling for Object Detection
We propose a dense object detector with an instance-wise sampling strategy, named IQDet.
Learning to Jointly Deblur, Demosaick and Denoise Raw Images
We address the problem of non-blind deblurring and demosaicking of noisy raw images.
Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
Motivated by our discovery, we propose a unified distribution alignment strategy for long-tail visual recognition.
Ranked #7 on
Long-tail Learning
on Places-LT
OTA: Optimal Transport Assignment for Object Detection
Recent advances in label assignment in object detection mainly seek to independently define positive/negative training samples for each ground-truth (gt) object.
Ranked #44 on
Object Detection
on COCO test-dev
Resilient Control under Quantization and Denial-of-Service: Co-designing a Deadbeat Controller and Transmission Protocol
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.
You Only Look One-level Feature
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}.
Ranked #101 on
Object Detection
on COCO test-dev
Training Networks in Null Space of Feature Covariance for Continual Learning
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.
End-to-End Human Object Interaction Detection with HOI Transformer
We propose HOI Transformer to tackle human object interaction (HOI) detection in an end-to-end manner.
Ranked #11 on
Human-Object Interaction Detection
on HICO-DET
(using extra training data)
Improving Text-to-SQL with Schema Dependency Learning
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.
FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation
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.
Using Long Short-Term Memory (LSTM) and Internet of Things (IoT) for localized surface temperature forecasting in an urban environment
Meanwhile, by using IoT observations, the spatial resolution of air temperature predictions is significantly improved.
Neural Architecture Search with Random Labels
In this paper, we investigate a new variant of neural architecture search (NAS) paradigm -- searching with random labels (RLNAS).
Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learning
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.
RepVGG: Making VGG-style ConvNets Great Again
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.
Ranked #16 on
Semantic Segmentation
on Cityscapes val
Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing
Semantic parsing has long been a fundamental problem in natural language processing.
Domain-Free Adversarial Splitting for Domain Generalization
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.
Implicit Feature Pyramid Network for Object Detection
In this paper, we present an implicit feature pyramid network (i-FPN) for object detection.
Efficient Human Pose Estimation by Learning Deeply Aggregated Representations
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.
Fine-Grained Dynamic Head for Object Detection
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.
Rethinking Learnable Tree Filter for Generic Feature Transform
The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation.
End-to-End Object Detection with Fully Convolutional Network
Mainstream object detectors based on the fully convolutional network has achieved impressive performance.
Fully Convolutional Networks for Panoptic Segmentation
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)
Dual Attention Network for Cross-lingual Entity Alignment
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.
Decentralized TD Tracking with Linear Function Approximation and its Finite-Time Analysis
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
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.
Ranked #1 on
Optical Flow Estimation
on KITTI 2012 unsupervised
Self-EMD: Self-Supervised Object Detection without ImageNet
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.
Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysis
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
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.
EqCo: Equivalent Rules for Self-supervised Contrastive Learning
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.
Activate or Not: Learning Customized Activation
We present a simple, effective, and general activation function we term ACON which learns to activate the neurons or not.
Deep Reinforcement Learning for Dynamic Spectrum Sensing and Aggregation in Multi-Channel Wireless Networks
Then, the vacant channels in the selected segment will be aggregated for satisfying the user requirement.
Multi-Frequency Multi-Scenario Millimeter Wave MIMO Channel Measurements and Modeling for B5G Wireless Communication Systems
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
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
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.
WeightNet: Revisiting the Design Space of Weight Networks
WeightNet is easy and memory-conserving to train, on the kernel space instead of the feature space.
Funnel Activation for Visual Recognition
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.
BorderDet: Border Feature for Dense Object Detection
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.
Learning from Manipulable Signals
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
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.
LabelEnc: A New Intermediate Supervision Method for Object Detection
In this paper we propose a new intermediate supervision method, named LabelEnc, to boost the training of object detection systems.
End-to-end Interpretable Learning of Non-blind Image Deblurring
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.
Learning Low-Resource End-To-End Goal-Oriented Dialog for Fast and Reliable System Deployment
Existing end-to-end dialog systems perform less effectively when data is scarce.
Structured and Localized Image Restoration
We present a novel approach to image restoration that leverages ideas from localized structured prediction and non-linear multi-task learning.
Online Reinforcement Learning Control by Direct Heuristic Dynamic Programming: from Time-Driven to Event-Driven
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
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
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.
Dynamic Memory Induction Networks for Few-Shot Text Classification
This paper proposes Dynamic Memory Induction Networks (DMIN) for few-shot text classification.
A Survey on Dialog Management: Recent Advances and Challenges
Dialog management (DM) is a crucial component in a task-oriented dialog system.
Angle-based Search Space Shrinking for Neural Architecture Search
Comprehensive experiments show that ABS can dramatically enhance existing NAS approaches by providing a promising shrunk search space.
Dynamic Scale Training for Object Detection
We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection.
Attentive Normalization for Conditional Image Generation
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.
Learning Human-Object Interaction Detection using Interaction Points
Human-object interaction (HOI) detection strives to localize both the human and an object as well as the identification of complex interactions between them.
Dynamic Region-Aware Convolution
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.
Learning Dynamic Routing for Semantic Segmentation
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.
Detection in Crowded Scenes: One Proposal, Multiple Predictions
We propose a simple yet effective proposal-based object detector, aiming at detecting highly-overlapped instances in crowded scenes.
Ranked #2 on
Pedestrian Detection
on TJU-Ped-campus
High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification
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.
PointINS: Point-based Instance Segmentation
In this paper, we explore the mask representation in instance segmentation with Point-of-Interest (PoI) features.
Learning Delicate Local Representations for Multi-Person Pose Estimation
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.
Gauss-Newton Unrolled Neural Networks and Data-driven Priors for Regularized PSSE with Robustness
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.
A Big Data Enabled Channel Model for 5G Wireless Communication Systems
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
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
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
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
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.
PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation
Our method is a natural extension of 2D-keypoint approaches that successfully work on RGB based 6DoF estimation.
Ranked #1 on
6D Pose Estimation
on YCB-Video
Conductor Galloping Prediction on Imbalanced Datasets: SVM with Smart Sampling
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
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.
Learnable Tree Filter for Structure-preserving Feature Transform
To this end, tree filtering modules are embedded to formulate a unified framework for semantic segmentation.
VAENAS: Sampling Matters in Neural Architecture Search
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.
Resizable Neural Networks
We introduce the adaptive resizable networks as dynamic networks, which further improve the performance with less computational cost via data-dependent inference.
Content-Aware Unsupervised Deep Homography Estimation
Homography estimation is a basic image alignment method in many applications.
Ranked #5 on
Homography Estimation
on S-COCO
Disentangled Image Matting
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.
HRGE-Net: Hierarchical Relational Graph Embedding Network for Multi-view 3D Shape Recognition
We construct a relational graph with multi-view images as nodes, and design relational graph embedding by modeling pairwise and neighboring relations among views.
DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation
This paper introduces an extremely efficient CNN architecture named DFANet for semantic segmentation under resource constraints.
Ranked #9 on
Semantic Segmentation
on CamVid
Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification
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).
Ranked #15 on
Person Re-Identification
on Market-1501-C
Single Path One-Shot Neural Architecture Search with Uniform Sampling
It is easy to train and fast to search.
Ranked #61 on
Neural Architecture Search
on ImageNet
ThunderNet: Towards Real-time Generic Object Detection
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.
Ranked #19 on
Object Detection
on PASCAL VOC 2007
DetNAS: Backbone Search for Object Detection
In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better backbones for object detection.
MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks.
Improving Cross-Domain Chinese Word Segmentation with Word Embeddings
Cross-domain Chinese Word Segmentation (CWS) remains a challenge despite recent progress in neural-based CWS.
Meta-SR: A Magnification-Arbitrary Network for Super-Resolution
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.
Induction Networks for Few-Shot Text Classification
Therefore, we should be able to learn a general representation of each class in the support set and then compare it to new queries.
Ranked #1 on
Few-Shot Text Classification
on ODIC 5-way (10-shot)
Rethinking on Multi-Stage Networks for Human Pose Estimation
Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods.
Ranked #1 on
Pose Estimation
on COCO minival
HyperAdam: A Learnable Task-Adaptive Adam for Network Training
Deep neural networks are traditionally trained using human-designed stochastic optimization algorithms, such as SGD and Adam.
Learning Spectral Transform Network on 3D Surface for Non-rigid Shape Analysis
Designing a network on 3D surface for non-rigid shape analysis is a challenging task.
Unpaired Brain MR-to-CT Synthesis using a Structure-Constrained CycleGAN
The cycleGAN is becoming an influential method in medical image synthesis.
Rendering Portraitures from Monocular Camera and Beyond
Specifically, we first exploit Convolutional Neural Networks to estimate the relative depth and portrait segmentation maps from a single input image.
Proximal Dehaze-Net: A Prior Learning-Based Deep Network for Single Image Dehazing
In this paper, we propose a novel deep learning approach for single image dehazing by learning dark channel and transmission priors.
GridFace: Face Rectification via Learning Local Homography Transformations
In this paper, we propose a method, called GridFace, to reduce facial geometric variations and improve the recognition performance.
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Datasets, Transforms and Models specific to Computer Vision
Ranked #1 on
Object Detection
on MPII Single Person
Unified Perceptual Parsing for Scene Understanding
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.
Ranked #59 on
Semantic Segmentation
on ADE20K val
MetaAnchor: Learning to Detect Objects with Customized Anchors
We propose a novel and flexible anchor mechanism named MetaAnchor for object detection frameworks.
Learning Visually-Grounded Semantics from Contrastive Adversarial Samples
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.
CrowdHuman: A Benchmark for Detecting Human in a Crowd
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)
DetNet: A Backbone network for Object Detection
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.
Automated vehicle's behavior decision making using deep reinforcement learning and high-fidelity simulation environment
Therefore, a framework of the decision-making training and learning is put forward in this paper.
ExFuse: Enhancing Feature Fusion for Semantic Segmentation
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)
AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
In this paper, we propose a novel method called AlignedReID that extracts a global feature which is jointly learned with local features.
Ranked #1 on
Person Re-Identification
on CUHK-SYSU
Repulsion Loss: Detecting Pedestrians in a Crowd
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)
Cascaded Pyramid Network for Multi-Person Pose Estimation
In this paper, we present a novel network structure called Cascaded Pyramid Network (CPN) which targets to relieve the problem from these "hard" keypoints.
Ranked #3 on
Multi-Person Pose Estimation
on COCO
Light-Head R-CNN: In Defense of Two-Stage Object Detector
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
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.
Neural Multi-Atlas Label Fusion: Application to Cardiac MR Images
There are two major challenges in this category of methods, i. e., atlas selection and label fusion.
Channel Pruning for Accelerating Very Deep Neural Networks
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
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).
Ranked #66 on
Person Re-Identification
on DukeMTMC-reID
ADMM-Net: A Deep Learning Approach for Compressive Sensing MRI
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.
Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network
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.
Ranked #7 on
Semantic Segmentation
on PASCAL VOC 2012 val
Deep Learning with Low Precision by Half-wave Gaussian Quantization
The problem of quantizing the activations of a deep neural network is considered.
Deep ADMM-Net for Compressive Sensing MRI
Compressive Sensing (CS) is an effective approach for fast Magnetic Resonance Imaging (MRI).
Supervised Transformer Network for Efficient Face Detection
For real-time performance, we run the cascaded network only on regions of interests produced from a boosting cascade face detector.
Ranked #6 on
Face Detection
on PASCAL Face
R-FCN: Object Detection via Region-based Fully Convolutional Networks
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.
Ranked #4 on
Real-Time Object Detection
on PASCAL VOC 2007
ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation
Large-scale data is of crucial importance for learning semantic segmentation models, but annotating per-pixel masks is a tedious and inefficient procedure.
Rich Image Captioning in the Wild
We present an image caption system that addresses new challenges of automatically describing images in the wild.
Instance-sensitive Fully Convolutional Networks
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.
Identity Mappings in Deep Residual Networks
Deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors.
Ranked #15 on
Image Classification
on Kuzushiji-MNIST
Instance-aware Semantic Segmentation via Multi-task Network Cascades
We develop an algorithm for the nontrivial end-to-end training of this causal, cascaded structure.
Ranked #3 on
Multi-Human Parsing
on PASCAL-Part
Deep Residual Learning for Image Recognition
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.
Ranked #2 on
Semantic Object Interaction Classification
on VLOG
Learning Discriminative Reconstructions for Unsupervised Outlier Removal
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
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.
Deep Representation of Facial Geometric and Photometric Attributes for Automatic 3D Facial Expression Recognition
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.
Harmonic Extension
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
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.
Ranked #5 on
Real-Time Object Detection
on PASCAL VOC 2007
A Geodesic-Preserving Method for Image Warping
The image projections will turn the straight lines into curved "geodesic lines", and it is fundamentally impossible to keep all these lines straight.
Cascaded Hand Pose Regression
We extends the previous 2D cascaded object pose regression work [9] in two aspects so that it works better for 3D articulated objects.
Sparse Projections for High-Dimensional Binary Codes
This paper addresses the problem of learning long binary codes from high-dimensional data.
Global Refinement of Random Forest
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
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.
Object Detection Networks on Convolutional Feature Maps
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.
Total Variation Regularized Tensor RPCA for Background Subtraction from Compressive Measurements
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
Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks.
Ranked #44 on
Semantic Segmentation
on PASCAL Context
Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal
In this paper, we address the problem of estimating and removing non-uniform motion blur from a single blurry image.
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
In this work, we study rectifier neural networks for image classification from two aspects.