Search Results for author:
Found 106 papers, 47 papers with code
Towards Accurate Post-training Network Quantization via Bit-Split and Stitching
Network quantization is essential for deploying deep models to IoT devices due to the high efficiency, no matter on special hardware like TPU or general hardware like CPU and GPU.
ProxyBNN: Learning Binarized Neural Networks via Proxy Matrices
The matrix composed of basis vectors is referred to as the proxy matrix, and auxiliary variables serve as the coefficients of this linear combination.
Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition
Nevertheless, how to efficiently model the spatial-temporal skeleton graph without introducing extra computation burden is a challenging problem for industrial deployment.
CSR-dMRI: Continuous Super-Resolution of Diffusion MRI with Anatomical Structure-assisted Implicit Neural Representation Learning
The first is the latent feature extractor, which primarily extracts latent space feature maps from LR dMRI and anatomical images while learning structural prior information from the anatomical images.
We Choose to Go to Space: Agent-driven Human and Multi-Robot Collaboration in Microgravity
We present SpaceAgents-1, a system for learning human and multi-robot collaboration (HMRC) strategies under microgravity conditions.
AID-DTI: Accelerating High-fidelity Diffusion Tensor Imaging with Detail-Preserving Model-based Deep Learning
Deep learning has shown great potential in accelerating diffusion tensor imaging (DTI).
Simultaneous q-Space Sampling Optimization and Reconstruction for Fast and High-fidelity Diffusion Magnetic Resonance Imaging
Diffusion Magnetic Resonance Imaging (dMRI) plays a crucial role in the noninvasive investigation of tissue microstructural properties and structural connectivity in the \textit{in vivo} human brain.
Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing
Multi-task reinforcement learning endeavors to accomplish a set of different tasks with a single policy.
Analyzing Generalization in Policy Networks: A Case Study with the Double-Integrator System
Extensive utilization of deep reinforcement learning (DRL) policy networks in diverse continuous control tasks has raised questions regarding performance degradation in expansive state spaces where the input state norm is larger than that in the training environment.
SpikingNeRF: Making Bio-inspired Neural Networks See through the Real World
In this paper, we propose SpikingNeRF, which aligns the radiance ray with the temporal dimension of SNN, to naturally accommodate the SNN to the reconstruction of Radiance Fields.
Temporal Action Localization with Enhanced Instant Discriminability
Temporal action detection (TAD) aims to detect all action boundaries and their corresponding categories in an untrimmed video.
Ranked #1 on
Temporal Action Localization
on MultiTHUMOS
Enhancing Your Trained DETRs with Box Refinement
We hope our work will bring the attention of the detection community to the localization bottleneck of current DETR-like models and highlight the potential of the RefineBox framework.
FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation
In FVP, the visual prompt is parameterized using only a small amount of low-frequency learnable parameters in the input frequency space, and is learned by minimizing the segmentation loss between the predicted segmentation of the prompted target image and reliable pseudo segmentation label of the target image under the frozen model.
HPN: Personalized Federated Hyperparameter Optimization
The client encoding is calculated with a random projection-based procedure to protect each client's privacy.
$\rm A^2Q$: Aggregation-Aware Quantization for Graph Neural Networks
Through an in-depth analysis of the topology of GNNs, we observe that the topology of the graph leads to significant differences between nodes, and most of the nodes in a graph appear to have a small aggregation value.
Poly-PC: A Polyhedral Network for Multiple Point Cloud Tasks at Once
In this work, we show that it is feasible to perform multiple tasks concurrently on point cloud with a straightforward yet effective multi-task network.
MDL-NAS: A Joint Multi-Domain Learning Framework for Vision Transformer
Technically, MDL-NAS constructs a coarse-to-fine search space, where the coarse search space offers various optimal architectures for different tasks while the fine search space provides fine-grained parameter sharing to tackle the inherent obstacles of multi-domain learning.
DATE: Dual Assignment for End-to-End Fully Convolutional Object Detection
In this paper, we revisit these two assignment methods and find that bringing one-to-many assignment back to end-to-end fully convolutional detectors helps with model convergence.
GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks
In this paper, we propose GLIF, a unified spiking neuron, to fuse different bio-features in different neuronal behaviors, enlarging the representation space of spiking neurons.
Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report
Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP).
AIM 2022 Challenge on Instagram Filter Removal: Methods and Results
This paper introduces the methods and the results of AIM 2022 challenge on Instagram Filter Removal.
AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results
The homepage of this challenge is at https://github. com/RenYang-home/AIM22_CompressSR.
PalQuant: Accelerating High-precision Networks on Low-precision Accelerators
In this paper, we propose the PArallel Low-precision Quantization (PalQuant) method that approximates high-precision computations via learning parallel low-precision representations from scratch.
PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient
First, the difference in feature magnitude between the teacher and the student could enforce overly strict constraints on the student.
Learning the policy for mixed electric platoon control of automated and human-driven vehicles at signalized intersection: a random search approach
Meanwhile, the simulation results demonstrate the effectiveness of the delay reward, which is designed to outperform distributed reward mechanism} Compared with normal car-following behavior, the sensitivity analysis reveals that the energy can be saved to different extends (39. 27%-82. 51%) by adjusting the relative importance of the optimization goal.
Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning
In this paper, we rethink the paradigm and explore a new regime: {\em fine-tuning a small part of parameters in the backbone}.
Ranked #8 on
Few-Shot Semantic Segmentation
on COCO-20i (1-shot)
Soft Threshold Ternary Networks
The latest STTN shows that ResNet-18 with ternary weights and ternary activations achieves up to 68. 2% Top-1 accuracy on ImageNet.
Efficient Virtual View Selection for 3D Hand Pose Estimation
3D hand pose estimation from single depth is a fundamental problem in computer vision, and has wide applications. However, the existing methods still can not achieve satisfactory hand pose estimation results due to view variation and occlusion of human hand.
Ranked #1 on
Hand Pose Estimation
on ICVL Hands
Differentially Private Federated Learning with Local Regularization and Sparsification
User-level differential privacy (DP) provides certifiable privacy guarantees to the information that is specific to any user's data in federated learning.
Network resilience in the aging brain
Degeneration and adaptation are two competing sides of the same coin called resilience in the progressive processes of brain aging or diseases.
Revisiting L1 Loss in Super-Resolution: A Probabilistic View and Beyond
Super-resolution as an ill-posed problem has many high-resolution candidates for a low-resolution input.
Q-ViT: Fully Differentiable Quantization for Vision Transformer
In this paper, we propose a fully differentiable quantization method for vision transformer (ViT) named as Q-ViT, in which both of the quantization scales and bit-widths are learnable parameters.
APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers
Showing how vision Transformers are at the risk of privacy leakage via gradients, we urge the significance of designing privacy-safer Transformer models and defending schemes.
DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy
In light of this missing, we propose the very first framework that employs neural architecture search to automatic model design for private deep learning, dubbed as DPNAS.
Joint Channel and Weight Pruning for Model Acceleration on Moblie Devices
In this paper, we present a unified framework with Joint Channel pruning and Weight pruning (JCW), and achieves a better Pareto-frontier between the latency and accuracy than previous model compression approaches.
Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization
Finally, based on the above simplification, we show that the original problem can be reformulated as a Multiple-Choice Knapsack Problem (MCKP) and propose a greedy search algorithm to solve it efficiently.
Improving Binary Neural Networks through Fully Utilizing Latent Weights
Binary Neural Networks (BNNs) rely on a real-valued auxiliary variable W to help binary training.
Revisiting Quantization Error in Face Alignment
The statistical re- sults show the NME generated by quantization error is even larger than 1/3 of the SOTA item, which is a serious obsta- cle for making a new breakthrough in face alignment.
Ranked #8 on
Face Alignment
on COFW
Architecture Aware Latency Constrained Sparse Neural Networks
Acceleration of deep neural networks to meet a specific latency constraint is essential for their deployment on mobile devices.
IntraLoss: Further Margin via Gradient-Enhancing Term for Deep Face Recognition
This method, named IntraLoss, explicitly performs gradient enhancement in the anisotropic region so that the intra-class distribution continues to shrink, resulting in isotropic and more compact intra-class distribution and further margin between identities.
Brain Age Estimation From MRI Using Cascade Networks with Ranking Loss
In this paper, a novel 3D convolutional network, called two-stage-age-network (TSAN), is proposed to estimate brain age from T1-weighted MRI data.
HIH: Towards More Accurate Face Alignment via Heatmap in Heatmap
In particular, our HIH reaches 4. 08 NME (Normalized Mean Error) on WFLW, and 3. 21 on COFW, which exceeds previous methods by a significant margin.
Ranked #4 on
Face Alignment
on WFW (Extra Data)
AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition
Existing methods for skeleton-based action recognition mainly focus on improving the recognition accuracy, whereas the efficiency of the model is rarely considered.
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 #142 on
Object Detection
on COCO test-dev
Adversarial Graph Disentanglement
For them, a component-specific aggregation approach is proposed to achieve micro-disentanglement by inferring latent components that cause the links between nodes.
Hardware Acceleration of Fully Quantized BERT for Efficient Natural Language Processing
BERT is the most recent Transformer-based model that achieves state-of-the-art performance in various NLP tasks.
Generative Zero-shot Network Quantization
Convolutional neural networks are able to learn realistic image priors from numerous training samples in low-level image generation and restoration.
Dynamic Dual Gating Neural Networks
In particular, dynamic dual gating can provide 59. 7% saving in computing of ResNet50 with 76. 41% top-1 accuracy on ImageNet, which has advanced the state-of-the-art.
Multi-Faceted Representation Learning with Hybrid Architecture for Time Series Classification
Time series classification problems exist in many fields and have been explored for a couple of decades.
Revisiting Parameter Sharing for Automatic Neural Channel Number Search
Nevertheless, it is unclear how parameter sharing affects the searching process.
AIM 2020 Challenge on Rendering Realistic Bokeh
This paper reviews the second AIM realistic bokeh effect rendering challenge and provides the description of the proposed solutions and results.
BGGAN: Bokeh-Glass Generative Adversarial Network for Rendering Realistic Bokeh
A photo captured with bokeh effect often means objects in focus are sharp while the out-of-focus areas are all blurred.
ATF: Towards Robust Face Alignment via Leveraging Similarity and Diversity across Different Datasets
Face alignment is an important task in the field of multi-media.
Ranked #9 on
Face Alignment
on COFW
(using extra training data)
Taking Modality-free Human Identification as Zero-shot Learning
There have been numerous methods proposed for human identification, such as face identification, person re-identification, and gait identification.
AIM 2020: Scene Relighting and Illumination Estimation Challenge
The first track considered one-to-one relighting; the objective was to relight an input photo of a scene with a different color temperature and illuminant orientation (i. e., light source position).
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results.
Faster Person Re-Identification
In this work, we introduce a new solution for fast ReID by formulating a novel Coarse-to-Fine (CtF) hashing code search strategy, which complementarily uses short and long codes, achieving both faster speed and better accuracy.
Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition
Besides, from the data aspect, we introduce a skeletal data decoupling technique to emphasize the specific characteristics of space/time and different motion scales, resulting in a more comprehensive understanding of the human actions. To test the effectiveness of the proposed method, extensive experiments are conducted on four challenging datasets for skeleton-based gesture and action recognition, namely, SHREC, DHG, NTU-60 and NTU-120, where DSTA-Net achieves state-of-the-art performance on all of them.
Ranked #27 on
Skeleton Based Action Recognition
on NTU RGB+D
What and Where: Modeling Skeletons from Semantic and Spatial Perspectives for Action Recognition
The two perspectives are orthogonal and complementary to each other; and by fusing them in a unified framework, our method achieves a more comprehensive understanding of the skeleton data.
TTPP: Temporal Transformer with Progressive Prediction for Efficient Action Anticipation
Video action anticipation aims to predict future action categories from observed frames.
From Anchor Generation to Distribution Alignment: Learning a Discriminative Embedding Space for Zero-Shot Recognition
In zero-shot learning (ZSL), the samples to be classified are usually projected into side information templates such as attributes.
Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification
Second, given cross-modality unpaired-images of a person, our method can generate cross-modality paired images from exchanged images.
A Comprehensive Study on Temporal Modeling for Online Action Detection
Online action detection (OAD) is a practical yet challenging task, which has attracted increasing attention in recent years.
Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks
Second, the second-order information of the skeleton data, i. e., the length and orientation of the bones, is rarely investigated, which is naturally more informative and discriminative for the human action recognition.
Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning
Graph representation learning aims to encode all nodes of a graph into low-dimensional vectors that will serve as input of many compute vision tasks.
Generative Adversarial Network
Graph Representation Learning
A Discriminative Learned CNN Embedding for Remote Sensing Image Scene Classification
Concretely, for remote sensing image scene classification, we would like to map images from the same scene to feature vectors that are close, and map images from different scenes to feature vectors that are widely separated.
Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision
Existing methods exploit the joint positions to extract the body-part features from the activation map of the convolutional networks to assist human action recognition.
Location-aware Upsampling for Semantic Segmentation
Many successful learning targets such as minimizing dice loss and cross-entropy loss have enabled unprecedented breakthroughs in segmentation tasks.
Ranked #35 on
Semantic Segmentation
on PASCAL Context
Convolutional Prototype Learning for Zero-Shot Recognition
The key to ZSL is to transfer knowledge from the seen to the unseen classes via auxiliary class attribute vectors.
SpatialFlow: Bridging All Tasks for Panoptic Segmentation
Object location is fundamental to panoptic segmentation as it is related to all things and stuff in the image scene.
Ranked #17 on
Panoptic Segmentation
on COCO test-dev
RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment
First, it can exploit pixel alignment and feature alignment jointly.
Cross-Modality Person Re-identification
Generative Adversarial Network
+2
A System-Level Solution for Low-Power Object Detection
As a case study, we evaluate our object detection system on a real-world surveillance video with input size of 512x512, and it turns out that the system can achieve an inference speed of 18 fps at the cost of 6. 9W (with display) with an mAP of 66. 4 verified on the PASCAL VOC 2012 dataset.
Compact Global Descriptor for Neural Networks
Long-range dependencies modeling, widely used in capturing spatiotemporal correlation, has shown to be effective in CNN dominated computer vision tasks.
Ranked #208 on
Object Detection
on COCO test-dev
Enhancing the Discriminative Feature Learning for Visible-Thermal Cross-Modality Person Re-Identification
To address these two issues, we propose focusing on enhancing the discriminative feature learning (EDFL) with two extreme simple means from two core aspects, (1) skip-connection for mid-level features incorporation to improve the person features with more discriminability and robustness, and (2) dual-modality triplet loss to guide the training procedures by simultaneously considering the cross-modality discrepancy and intra-modality variations.
Cross-Modality Person Re-identification
Person Re-Identification
Edge Heuristic GAN for Non-uniform Blind Deblurring
Non-uniform blur, mainly caused by camera shake and motions of multiple objects, is one of the most common causes of image quality degradation.
Non-Local Graph Convolutional Networks for Skeleton-Based Action Recognition
However, the topology of the graph is set by hand and fixed over all layers, which may be not optimal for the action recognition task and the hierarchical CNN structures.
Ranked #55 on
Skeleton Based Action Recognition
on NTU RGB+D
Overcoming the bottleneck in traditional assessments of verbal memory: Modeling human ratings and classifying clinical group membership
A final set of three features were used to both predict expert human ratings with a ridge regression model (r = 0. 88) and to differentiate patients from healthy individuals with an ensemble of logistic regression classifiers (accuracy = 76{\%}).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Attention: A Big Surprise for Cross-Domain Person Re-Identification
Unlike existing cross-domain Re-ID methods, leveraging the auxiliary information of those unlabeled target-domain data, we aim at enhancing the model generalization and adaptation by discriminative feature learning, and directly exploiting a pre-trained model to new domains (datasets) without any utilization of the information from target domains.
The General Pair-based Weighting Loss for Deep Metric Learning
A large amount of loss functions based on pair distances have been presented in the literature for guiding the training of deep metric learning.
Semi-supervised Learning with Contrastive Predicative Coding
Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain.
Temporal Action Detection by Joint Identification-Verification
Temporal action detection aims at not only recognizing action category but also detecting start time and end time for each action instance in an untrimmed video.
Graph Convolutional Neural Networks based on Quantum Vertex Saliency
This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes.
Training Binary Weight Networks via Semi-Binary Decomposition
In this paper, we propose a novel semi-binary decomposition method which decomposes a matrix into two binary matrices and a diagonal matrix.
Semi-Supervised Generative Adversarial Hashing for Image Retrieval
Secondly, we design novel structure of the generative model and the discriminative model to learn the distribution of triplet-wise information in a semi-supervised way.
Deep Continuous Conditional Random Fields with Asymmetric Inter-object Constraints for Online Multi-object Tracking
In addition, inter-object relations are mostly modeled in a symmetric way, which we argue is not an optimal setting.
Two-Step Quantization for Low-Bit Neural Networks
In this paper, we propose a simple yet effective Two-Step Quantization (TSQ) framework, by decomposing the network quantization problem into two steps: code learning and transformation function learning based on the learned codes.
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition
In addition, the second-order information (the lengths and directions of bones) of the skeleton data, which is naturally more informative and discriminative for action recognition, is rarely investigated in existing methods.
Ranked #5 on
Skeleton Based Action Recognition
on UAV-Human
PCN: Part and Context Information for Pedestrian Detection with CNNs
To take advantage of the body parts and context information for pedestrian detection, we propose the part and context network (PCN) in this work.
From Hashing to CNNs: Training BinaryWeight Networks via Hashing
To achieve this goal, we propose a novel approach named BWNH to train Binary Weight Networks via Hashing.
Recent Advances in Efficient Computation of Deep Convolutional Neural Networks
As for hardware implementation of deep neural networks, a batch of accelerators based on FPGA/ASIC have been proposed in recent years.
Additive Margin Softmax for Face Verification
In this work, we introduce a novel additive angular margin for the Softmax loss, which is intuitively appealing and more interpretable than the existing works.
Ranked #2 on
Face Identification
on Trillion Pairs Dataset
Egocentric Gesture Recognition Using Recurrent 3D Convolutional Neural Networks With Spatiotemporal Transformer Modules
Gesture is a natural interface in interacting with wearable devices such as VR/AR helmet and glasses.
Director Field Analysis (DFA): Exploring Local White Matter Geometric Structure in diffusion MRI
2) We propose Orientational Order (OO) and Orientational Dispersion (OD) indices to describe the degree of alignment and dispersion of a spherical function in a single voxel or in a region, respectively; 3) We also show how to construct a local orthogonal coordinate frame in each voxel exhibiting anisotropic diffusion; 4) Finally, we define three indices to describe three types of orientational distortion (splay, bend, and twist) in a local spatial neighborhood, and a total distortion index to describe distortions of all three types.
NormFace: L2 Hypersphere Embedding for Face Verification
We show that both strategies, and small variants, consistently improve performance by between 0. 2% to 0. 4% on the LFW dataset based on two models.
Regularizing Face Verification Nets For Pain Intensity Regression
In this way, the expression intensity regression task can benefit from the rich feature representations trained on a huge amount of data for face verification.
Fixed-point Factorized Networks
In recent years, Deep Neural Networks (DNN) based methods have achieved remarkable performance in a wide range of tasks and have been among the most powerful and widely used techniques in computer vision.
Quantized Convolutional Neural Networks for Mobile Devices
Recently, convolutional neural networks (CNN) have demonstrated impressive performance in various computer vision tasks.
Online Sketching Hashing
Recently, hashing based approximate nearest neighbor (ANN) search has attracted much attention.
Fast and Accurate Image Matching with Cascade Hashing for 3D Reconstruction
Image matching is one of the most challenging stages in 3D reconstruction, which usually occupies half of computational cost and inaccurate matching may lead to failure of reconstruction.
Regularized Spherical Polar Fourier Diffusion MRI with Optimal Dictionary Learning
Compared with the start-of-the-art CR-DL and DR-DL methods proposed by Merlet et al. and Bilgic et al., espectively, our work offers the following advantages.
