Search Results for author:
Found 371 papers, 131 papers with code
Momentum Batch Normalization for Deep Learning with Small Batch Size
To make a deeper understanding of BN, in this work we prove that BN actually introduces a certain level of noise into the sample mean and variance during the training process, while the noise level depends only on the batch size.
LST-Net: Learning a Convolutional Neural Network with a Learnable Sparse Transform
The 2D convolutional (Conv2d) layer is the fundamental element to a deep convolutional neural network (CNN).
A Decoupled Learning Scheme for Real-world Burst Denoising from Raw Images
On one hand, most of the models are trained on video sequences with synthetic noise.
Multiple Domain Cyberspace Attack and Defense Game Based on Reward Randomization Reinforcement Learning
In order to improve the defense ability of defender, a game model based on reward randomization reinforcement learning is proposed.
KGRGRL: A User's Permission Reasoning Method Based on Knowledge Graph Reward Guidance Reinforcement Learning
Following that, we proposed a user's permissions reasoning method based on reinforcement learning.
SwinFuse: A Residual Swin Transformer Fusion Network for Infrared and Visible Images
The existing deep learning fusion methods mainly concentrate on the convolutional neural networks, and few attempts are made with transformer.
OTExtSum: Extractive Text Summarisation with Optimal Transport
Optimal sentence extraction is conceptualised as obtaining an optimal summary that minimises the transportation cost to a given document regarding their semantic distributions.
Dense Learning based Semi-Supervised Object Detection
Semi-supervised object detection (SSOD) aims to facilitate the training and deployment of object detectors with the help of a large amount of unlabeled data.
Rapid model transfer for medical image segmentation via iterative human-in-the-loop update: from labelled public to unlabelled clinical datasets for multi-organ segmentation in CT
Despite the remarkable success on medical image analysis with deep learning, it is still under exploration regarding how to rapidly transfer AI models from one dataset to another for clinical applications.
Towards Reliable Image Outpainting: Learning Structure-Aware Multimodal Fusion with Depth Guidance
Image outpainting technology generates visually reasonable content regardless of authenticity, making it unreliable to serve for practical applications even though introducing additional modalities eg.
Adaptive Network Combination for Single-Image Reflection Removal: A Domain Generalization Perspective
Meanwhile, diverse testing sets are also provided with different types of reflection and scenes.
Large-Scale Pre-training for Person Re-identification with Noisy Labels
Since theses ID labels automatically derived from tracklets inevitably contain noises, we develop a large-scale Pre-training framework utilizing Noisy Labels (PNL), which consists of three learning modules: supervised Re-ID learning, prototype-based contrastive learning, and label-guided contrastive learning.
Ranked #5 on
Person Re-Identification
on CUHK03
Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution
Specifically, a tiny regression network is employed to predict the degradation parameters of the input image, while several convolutional experts with the same topology are jointly optimized to specify the network parameters via a non-linear mixture of experts.
Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds
VoxSeT is built upon a voxel-based set attention (VSA) module, which reduces the self-attention in each voxel by two cross-attentions and models features in a hidden space induced by a group of latent codes.
Towards Robust 2D Convolution for Reliable Visual Recognition
2D convolution (Conv2d), which is responsible for extracting features from the input image, is one of the key modules of a convolutional neural network (CNN).
Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation
One popular solution to this challenging task is self-training, which selects high-scoring predictions on target samples as pseudo labels for training.
Beyond a Video Frame Interpolator: A Space Decoupled Learning Approach to Continuous Image Transition
Most of the existing deep learning based VFI methods adopt off-the-shelf optical flow algorithms to estimate the bidirectional flows and interpolate the missing frames accordingly.
A Dual Weighting Label Assignment Scheme for Object Detection
Existing LA methods mostly focus on the design of pos weighting function, while the neg weight is directly derived from the pos weight.
Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution
In this paper, we demonstrate that it is possible to train a GAN-based SISR model which can stably generate perceptually realistic details while inhibiting visual artifacts.
A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution
The semantics of the text are firstly extracted by a text recognition module as text prior information.
A Differentiable Two-stage Alignment Scheme for Burst Image Reconstruction with Large Shift
Denoising and demosaicking are two essential steps to reconstruct a clean full-color image from the raw data.
Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization
In this work, we, for the first time to our best knowledge, propose to perform Exact Feature Distribution Matching (EFDM) by exactly matching the empirical Cumulative Distribution Functions (eCDFs) of image features, which could be implemented by applying the Exact Histogram Matching (EHM) in the image feature space.
Efficient Long-Range Attention Network for Image Super-resolution
A highly efficient long-range attention block (ELAB) is then built by simply cascading two shift-conv with a GMSA module, which is further accelerated by using a shared attention mechanism.
One-stage Video Instance Segmentation: From Frame-in Frame-out to Clip-in Clip-out
Based on the fact that adjacent frames in a short clip are highly coherent in content, we propose to extend the one-stage FiFo framework to a clip-in clip-out (CiCo) one, which performs VIS clip by clip.
Unfolded Deep Kernel Estimation for Blind Image Super-resolution
Nonetheless, the existing deep unfolding methods cannot explicitly solve the data term of the unfolding objective function, limiting their capability in blur kernel estimation.
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
Compared to other models on the leaderboard, DINO significantly reduces its model size and pre-training data size while achieving better results.
Ranked #1 on
14
on DDB14
Vision-Language Intelligence: Tasks, Representation Learning, and Large Models
This survey is inspired by the remarkable progress in both computer vision and natural language processing, and recent trends shifting from single modality processing to multiple modality comprehension.
DN-DETR: Accelerate DETR Training by Introducing Query DeNoising
Our method is universal and can be easily plugged into any DETR-like methods by adding dozens of lines of code to achieve a remarkable improvement.
BP-Triplet Net for Unsupervised Domain Adaptation: A Bayesian Perspective
In our work, considering the different importance of pair-wise samples for both feature learning and domain alignment, we deduce our BP-Triplet loss for effective UDA from the perspective of Bayesian learning.
Winograd Convolution: A Perspective from Fault Tolerance
Winograd convolution is originally proposed to reduce the computing overhead by converting multiplication in neural network (NN) with addition via linear transformation.
Adversarial Examples for Good: Adversarial Examples Guided Imbalanced Learning
Adversarial examples are inputs for machine learning models that have been designed by attackers to cause the model to make mistakes.
DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR
We present in this paper a novel query formulation using dynamic anchor boxes for DETR (DEtection TRansformer) and offer a deeper understanding of the role of queries in DETR.
Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation
In addition, such practice of re-identification still can not track those highly occluded objects when they are missed by the detector.
Ranked #6 on
Multi-Object Tracking
on MOT16
(using extra training data)
DeePN$^2$: A deep learning-based non-Newtonian hydrodynamic model
A long standing problem in the modeling of non-Newtonian hydrodynamics of polymeric flows is the availability of reliable and interpretable hydrodynamic models that faithfully encode the underlying micro-scale polymer dynamics.
CausalMTA: Eliminating the User Confounding Bias for Causal Multi-touch Attribution
Existing methods first train a model to predict the conversion probability of the advertisement journeys with historical data and calculate the attribution of each touchpoint using counterfactual predictions.
Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions
Though deep learning-based object detection methods have achieved promising results on the conventional datasets, it is still challenging to locate objects from the low-quality images captured in adverse weather conditions.
Few-shot Multi-hop Question Answering over Knowledge Base
In addition, in order to test the few-shot learning capability of our model, we ramdomly select 10% of the primary data to train our model, the result shows that our model can still achieves F1-score of 58. 54%, which verifies the capability of our model to process KBQA task and the advantage in few-shot Learning.
High-Resolution Programmable Scattering for Wireless Coverage Enhancement: An Indoor Field Trial Campaign
This work explores the potential for reconfigurable intelligent surface (RIS) deployment to mitigate non-line of sight effects in an indoor wireless communications.
Subspace Decomposition based DNN algorithm for elliptic-type multi-scale PDEs
Numerical results show that the SD$^2$NN model is superior to existing models such as MscaleDNN.
Grounded Language-Image Pre-training
The unification brings two benefits: 1) it allows GLIP to learn from both detection and grounding data to improve both tasks and bootstrap a good grounding model; 2) GLIP can leverage massive image-text pairs by generating grounding boxes in a self-training fashion, making the learned representation semantic-rich.
Ranked #1 on
Phrase Grounding
on Flickr30k Entities Test
(using extra training data)
Intelligent Reflecting Surface-induced Randomness for mmWave Key Generation
When considering the IRS weights are continuous and discrete uniformly distributed, we find that the reflection channel variance is equal to the number of IRS elements.
SVBRDF Recovery From a Single Image With Highlights using a Pretrained Generative Adversarial Network
For efficiency, we train the network in two stages: reusing a trained model to initialize the SVBRDFs and fine-tune it based on the input image.
Unsupervised Finetuning
This problem is more challenging than the supervised counterpart, as the low data density in the small-scale target data is not friendly for unsupervised learning, leading to the damage of the pretrained representation and poor representation in the target domain.
Early Melanoma Diagnosis with Sequential Dermoscopic Images
In this study, we propose a framework for automated early melanoma diagnosis using sequential dermoscopic images.
PWG-IDS: An Intrusion Detection Model for Solving Class Imbalance in IIoT Networks Using Generative Adversarial Networks
To address this imbalance, an intrusion detection system called pretraining Wasserstein generative adversarial network intrusion detection system (PWG-IDS) is proposed in this paper.
Mutual Consistency Learning for Semi-supervised Medical Image Segmentation
In this way, we minimize the discrepancy of multiple outputs (i. e., the model uncertainty) during training and force the model to generate invariant results in such challenging regions, aiming at capturing more useful features.
Semantic Segmentation
Semi-supervised Medical Image Segmentation
Layer-wise Customized Weak Segmentation Block and AIoU Loss for Accurate Object Detection
The anchor-based detectors handle the problem of scale variation by building the feature pyramid and directly setting different scales of anchors on each cell in different layers.
Reconcile Prediction Consistency for Balanced Object Detection
The Harmonic loss enables these two branches to supervise and promote each other during training, thereby producing consistent predictions with high co-occurrence of top classification and localization in the inference phase.
Term Interrelations and Trends in Software Engineering
The Software Engineering (SE) community is prolific, making it challenging for experts to keep up with the flood of new papers and for neophytes to enter the field.
Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting
In crowd counting, due to the problem of laborious labelling, it is perceived intractability of collecting a new large-scale dataset which has plentiful images with large diversity in density, scene, etc.
MicroNet: Improving Image Recognition with Extremely Low FLOPs
This paper aims at addressing the problem of substantial performance degradation at extremely low computational cost (e. g. 5M FLOPs on ImageNet classification).
Ultralow complexity long short-term memory network for fiber nonlinearity mitigation in coherent optical communication systems
In this paper, we propose a center-oriented long short-term memory network (Co-LSTM) incorporating a simplified mode with a recycling mechanism in the equalization operation, which can mitigate fiber nonlinearity in coherent optical communication systems with ultralow complexity.
On the Robustness of Domain Adaption to Adversarial Attacks
State-of-the-art deep neural networks (DNNs) have been proved to have excellent performance on unsupervised domain adaption (UDA).
MedAI at SemEval-2021 Task 10: Negation-aware Pre-training for Source-free Negation Detection Domain Adaptation
Due to the increasing concerns for data privacy, source-free unsupervised domain adaptation attracts more and more research attention, where only a trained source model is assumed to be available, while the labeled source data remain private.
Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth
Current geometry-based monocular 3D object detection models can efficiently detect objects by leveraging perspective geometry, but their performance is limited due to the absence of accurate depth information.
Image Scene Graph Generation (SGG) Benchmark
There is a surge of interest in image scene graph generation (object, attribute and relationship detection) due to the need of building fine-grained image understanding models that go beyond object detection.
Improve Unsupervised Pretraining for Few-label Transfer
Unsupervised pretraining has achieved great success and many recent works have shown unsupervised pretraining can achieve comparable or even slightly better transfer performance than supervised pretraining on downstream target datasets.
Query2Label: A Simple Transformer Way to Multi-Label Classification
The use of Transformer is rooted in the need of extracting local discriminative features adaptively for different labels, which is a strongly desired property due to the existence of multiple objects in one image.
Ranked #1 on
Multi-Label Classification
on PASCAL VOC 2012
Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks
Deep learning's performance has been extensively recognized recently.
Conditional Directed Graph Convolution for 3D Human Pose Estimation
Based on this representation, we further propose a spatial-temporal conditional directed graph convolution to leverage varying non-local dependence for different poses by conditioning the graph topology on input poses.
Ranked #5 on
3D Human Pose Estimation
on Human3.6M
Sliding Spectrum Decomposition for Diversified Recommendation
Content feed, a type of product that recommends a sequence of items for users to browse and engage with, has gained tremendous popularity among social media platforms.
NTIRE 2021 Multi-modal Aerial View Object Classification Challenge
In this paper, we introduce the first Challenge on Multi-modal Aerial View Object Classification (MAVOC) in conjunction with the NTIRE 2021 workshop at CVPR.
Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel
To address the above issues, this paper proposes a model-based blind SISR method under the probabilistic framework, which elaborately models image degradation from the perspectives of noise and blur kernel.
Text Prior Guided Scene Text Image Super-resolution
Our experiments on the benchmark TextZoom dataset show that TPGSR can not only effectively improve the visual quality of scene text images, but also significantly improve the text recognition accuracy over existing STISR methods.
VirFace: Enhancing Face Recognition via Unlabeled Shallow Data
In this paper, we propose a novel face recognition method, named VirFace, to effectively apply the unlabeled shallow data for face recognition.
Interactive Self-Training With Mean Teachers for Semi-Supervised Object Detection
Specifically, to alleviate the instability among the detection results in different iterations, we propose using nonmaximum suppression to fuse the detection results from different iterations.
Deep Convolutional Dictionary Learning for Image Denoising
Inspired by the great success of deep neural networks (DNNs), many unfolding methods have been proposed to integrate traditional image modeling techniques, such as dictionary learning (DicL) and sparse coding, into DNNs for image restoration.
Virtual Fully-Connected Layer: Training a Large-Scale Face Recognition Dataset With Limited Computational Resources
This is because the classification paradigm needs to train a fully connected layer as the category classifier, and its parameters will be in the hundreds of millions if the training dataset contains millions of identities.
Learning Tensor Low-Rank Prior for Hyperspectral Image Reconstruction
Snapshot hyperspectral imaging has been developed to capture the spectral information of dynamic scenes.
Gradual Domain Adaptation via Self-Training of Auxiliary Models
Domain adaptation becomes more challenging with increasing gaps between source and target domains.
Domain Adaptive SiamRPN++ for Object Tracking in the Wild
The SDA module aligns the feature representations of the tracking target's appearance to eliminate the semantic-level domain shift.
Dynamic Head: Unifying Object Detection Heads with Attentions
In this paper, we present a novel dynamic head framework to unify object detection heads with attentions.
Ranked #7 on
Object Detection
on COCO test-dev
Chasing Sparsity in Vision Transformers: An End-to-End Exploration
For example, our sparsified DeiT-Small at (5%, 50%) sparsity for (data, architecture), improves 0. 28% top-1 accuracy, and meanwhile enjoys 49. 32% FLOPs and 4. 40% running time savings.
Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners
Especially, state-of-the-art SSL methods significantly outperform existing UDA methods on the challenging UDA benchmark of DomainNet, and state-of-the-art UDA methods could be further enhanced with SSL techniques.
Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents
Faceted summarization provides briefings of a document from different perspectives.
Ranked #1 on
Unsupervised Extractive Summarization
on FacetSum
Unsupervised Part Segmentation through Disentangling Appearance and Shape
We study the problem of unsupervised discovery and segmentation of object parts, which, as an intermediate local representation, are capable of finding intrinsic object structure and providing more explainable recognition results.
High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network
Existing image-to-image translation (I2IT) methods are either constrained to low-resolution images or long inference time due to their heavy computational burden on the convolution of high-resolution feature maps.
Ranked #1 on
Photo Retouching
on MIT-Adobe 5k (1080p)
PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency
HRP requires that more attention should be paid to human regions, while GLC requires that a group of portrait photos should be retouched to a consistent tone.
HiDeNN-PGD: reduced-order hierarchical deep learning neural networks
This paper presents a proper generalized decomposition (PGD) based reduced-order model of hierarchical deep-learning neural networks (HiDeNN).
GAN Prior Embedded Network for Blind Face Restoration in the Wild
The proposed GAN prior embedded network (GPEN) is easy-to-implement, and it can generate visually photo-realistic results.
Ranked #1 on
Blind Face Restoration
on CelebA-HQ
Estimation of 3D Human Pose Using Prior Knowledge
Estimating three-dimensional human poses from the positions of two-dimensional joints has shown promising results. However, using two-dimensional joint coordinates as input loses more information than image-based approaches and results in ambiguity. In order to overcome this problem, we combine bone length and camera parameters with two-dimensional joint coordinates for input. This combination is more discriminative than the two-dimensional joint coordinates in that it can improve the accuracy of the model's prediction depth and alleviate the ambiguity that comes from projecting three-dimensional coordinates into two-dimensional space.
SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networks
To this end, we propose to learn implicit surface reconstruction by sign-agnostic optimization of convolutional occupancy networks, to simultaneously achieve advanced scalability to large-scale scenes, generality to novel shapes, and applicability to raw scans in a unified framework.
CAT: Cross-Attention Transformer for One-Shot Object Detection
Given a query patch from a novel class, one-shot object detection aims to detect all instances of that class in a target image through the semantic similarity comparison.
Discover the Hidden Attack Path in Multi-domain Cyberspace Based on Reinforcement Learning
To achieve these results, we pose discovering attack paths as a Reinforcement Learning (RL) problem and train an agent to discover multi-domain cyberspace attack paths.
Lite-HRNet: A Lightweight High-Resolution Network
We introduce a lightweight unit, conditional channel weighting, to replace costly pointwise (1x1) convolutions in shuffle blocks.
Ranked #22 on
Pose Estimation
on COCO test-dev
Smart and Secure CAV Networks Empowered by AI-Enabled Blockchain: The Next Frontier for Intelligent Safe Driving Assessment
Securing safe driving for connected and autonomous vehicles (CAVs) continues to be a widespread concern, despite various sophisticated functions delivered by artificial intelligence for in-vehicle devices.
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation
To further explore temporal correlation among video frames, we aggregate a temporal fusion module to infer instance masks from each frame to its adjacent frames, which helps our framework to handle challenging videos such as motion blur, partial occlusion and unusual object-to-camera poses.
CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning
This work concerns video-language pre-training and representation learning.
DAP: Detection-Aware Pre-training with Weak Supervision
This paper presents a detection-aware pre-training (DAP) approach, which leverages only weakly-labeled classification-style datasets (e. g., ImageNet) for pre-training, but is specifically tailored to benefit object detection tasks.
Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction
This paper focuses on the task of 4D shape reconstruction from a sequence of point clouds.
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding
This paper presents a new Vision Transformer (ViT) architecture Multi-Scale Vision Longformer, which significantly enhances the ViT of \cite{dosovitskiy2020image} for encoding high-resolution images using two techniques.
Ranked #23 on
Instance Segmentation
on COCO minival
CvT: Introducing Convolutions to Vision Transformers
We present in this paper a new architecture, named Convolutional vision Transformer (CvT), that improves Vision Transformer (ViT) in performance and efficiency by introducing convolutions into ViT to yield the best of both designs.
Ranked #1 on
Image Classification
on Flowers-102
(using extra training data)
HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset
Secondly, we conduct more sophisticated alignment and temporal fusion in the feature space of the coarse HDR video to produce better reconstruction.
Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases.
Ranked #5 on
Long-tail Learning
on CIFAR-100-LT (ρ=10)
Dynamic Weighted Learning for Unsupervised Domain Adaptation
These methods, however, ignore the interaction between domain alignment learning and class discrimination learning.
Pluggable Weakly-Supervised Cross-View Learning for Accurate Vehicle Re-Identification
Learning cross-view consistent feature representation is the key for accurate vehicle Re-identification (ReID), since the visual appearance of vehicles changes significantly under different viewpoints.
Low-Complexity Symbol Detection and Interference Cancellation for OTFS System
Orthogonal time frequency space (OTFS) is a two-dimensional modulation scheme realized in the delay- Doppler domain, which targets the robust wireless transmissions in high-mobility environments.
Training a First-Order Theorem Prover from Synthetic Data
A major challenge in applying machine learning to automated theorem proving is the scarcity of training data, which is a key ingredient in training successful deep learning models.
Semi-supervised Left Atrium Segmentation with Mutual Consistency Training
Such mutual consistency encourages the two decoders to have consistent and low-entropy predictions and enables the model to gradually capture generalized features from these unlabeled challenging regions.
Generalized Rough Polyharmonic Splines for Multiscale PDEs with Rough Coefficients
In this paper, we demonstrate the construction of generalized Rough Polyhamronic Splines (GRPS) within the Bayesian framework, in particular, for multiscale PDEs with rough coefficients.
Numerical Analysis Numerical Analysis
Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning
Visual search, recommendation, and contrastive similarity learning power technologies that impact billions of users worldwide.
Dual MINE-based Neural Secure Communications under Gaussian Wiretap Channel
The security constraints of this method is constructed only with the input and output signal samples of the legal and eavesdropper channels and benefit that training the encoder is completely independent of the decoder.
Constructing Evacuation Evolution Patterns and Decisions Using Mobile Device Location Data: A Case Study of Hurricane Irma
Moreover, our analysis revealed the importance of the individuals' mobility behavior in modeling the evacuation decision choice.
Measurement of the absolute branching fractions for purely leptonic $D_s^+$ decays
Constraining our measurement to the Standard Model expectation of lepton universality ($R=9. 75$), we find the more precise results $\cal B(D_s^+\to \tau^+\nu_\tau) = (5. 22\pm0. 10\pm 0. 14)\times10^{-2}$ and $A_{\it CP}(\tau^\pm\nu_\tau) = (-0. 1\pm1. 9\pm1. 0)\%$.
High Energy Physics - Experiment
Cross section measurement of $e^+e^- \to p\bar{p}η$ and $e^+e^- \to p\bar{p}ω$ at center-of-mass energies between 3.773 GeV and 4.6 GeV
Based on $14. 7~\textrm{fb}^{-1}$ of $e^+e^-$ annihilation data collected with the BESIII detector at the BEPCII collider at 17 different center-of-mass energies between $3. 7730~\textrm{GeV}$ and $4. 5995~\textrm{GeV}$, Born cross sections of the two processes $e^+e^- \to p\bar{p}\eta$ and $e^+e^- \to p\bar{p}\omega$ are measured for the first time.
High Energy Physics - Experiment
Resource Allocation for Mixed Numerology NOMA
Non-orthogonal multiple access (NOMA) techniques can potentially be used to accommodate users with different numerologies while also gaining the performance benefits associated with NOMA.
BE-RAN: Blockchain-enabled Open RAN with Decentralized Identity Management and Privacy-Preserving Communication
In this paper, Blockchain-enabled Radio Access Networks (BE-RAN) is proposed as a novel decentralized RAN architecture to facilitate enhanced security and privacy on identification and authentication.
Cryptography and Security Distributed, Parallel, and Cluster Computing Networking and Internet Architecture
Solution landscapes of the diblock copolymer-homopolymer model under two-dimensional confinement
We investigate the solution landscapes of the confined diblock copolymer and homopolymer in two-dimensional domain by using the extended Ohta--Kawasaki model.
Soft Condensed Matter Computational Physics
Joint Denoising and Demosaicking with Green Channel Prior for Real-world Burst Images
Considering the fact that the green channel has twice the sampling rate and better quality than the red and blue channels in CFA raw data, we propose to use this green channel prior (GCP) to build a GCP-Net for the JDD-B task.
Registration-based model reduction in complex two-dimensional geometries
We present a general -- i. e., independent of the underlying equation -- registration procedure for parameterized model order reduction.
Numerical Analysis Numerical Analysis 65N30, 41A45, 35J20, 90C26 G.1.8
Snapshot Hyperspectral Imaging Based on Weighted High-order Singular Value Regularization
In this paper, we propose an effective high-order tensor optimization based method to boost the reconstruction fidelity for snapshot hyperspectral imaging.
On Liouville systems at critical parameters, Part 2: Multiple bubbles
In this paper, we continue to consider the generalized Liouville system: $$ \Delta_g u_i+\sum_{j=1}^n a_{ij}\rho_j\left(\frac{h_j e^{u_j}}{\int h_j e^{u_j}}- {1} \right)=0\quad\text{in \,}M,\quad i\in I=\{1,\cdots, n\}, $$ where $(M, g)$ is a Riemann surface $M$ with volume $1$, $h_1,.., h_n$ are positive smooth functions and $\rho_j\in \mathbb R^+$($j\in I$).
Analysis of PDEs Mathematical Physics Mathematical Physics 35J60, 35J55
Hybrid Trilinear and Bilinear Programming for Aligning Partially Overlapping Point Sets
Alignment methods which can handle partially overlapping point sets and are invariant to the corresponding transformations are desirable in computer vision, with applications such as providing initial transformation configuration for local search based methods like ICP.
SEED: Self-supervised Distillation For Visual Representation
This paper is concerned with self-supervised learning for small models.
Unsupervised Domain Adaptation of Black-Box Source Models
Unsupervised domain adaptation (UDA) aims to learn models for a target domain of unlabeled data by transferring knowledge from a labeled source domain.
Reinforcement Learning for Flexibility Design Problems
Flexibility design problems are a class of problems that appear in strategic decision-making across industries, where the objective is to design a ($e. g.$, manufacturing) network that affords flexibility and adaptivity.
VinVL: Revisiting Visual Representations in Vision-Language Models
In our experiments we feed the visual features generated by the new object detection model into a Transformer-based VL fusion model \oscar \cite{li2020oscar}, and utilize an improved approach \short\ to pre-train the VL model and fine-tune it on a wide range of downstream VL tasks.
Ranked #5 on
Image Captioning
on nocaps-val-overall
Dynamic DETR: End-to-End Object Detection With Dynamic Attention
To mitigate the second limitation of learning difficulty, we introduce a dynamic decoder by replacing the cross-attention module with a ROI-based dynamic attention in the Transformer decoder.
Real-World Video Super-Resolution: A Benchmark Dataset and a Decomposition Based Learning Scheme
Existing VSR methods are mostly trained and evaluated on synthetic datasets, where the LR videos are uniformly downsampled from their high-resolution (HR) counterparts by some simple operators (e. g., bicubic downsampling).
AC-VAE: Learning Semantic Representation with VAE for Adaptive Clustering
Experimental evaluations show that the proposed method outperforms state-of-the-art representation learning methods in terms of neighbor clustering accuracy.