Search Results for author:
Found 279 papers, 98 papers with code
V2A-Mark: Versatile Deep Visual-Audio Watermarking for Manipulation Localization and Copyright Protection
Meanwhile, we introduce a sample-level audio localization method and a cross-modal copyright extraction mechanism to couple the information of audio and video frames.
ResVR: Joint Rescaling and Viewport Rendering of Omnidirectional Images
With the advent of virtual reality technology, omnidirectional image (ODI) rescaling techniques are increasingly embraced for reducing transmitted and stored file sizes while preserving high image quality.
Face2Face: Label-driven Facial Retouching Restoration
This poses challenges for fields that place high demands on the authenticity of photographs, such as identity verification and social media.
OmniSSR: Zero-shot Omnidirectional Image Super-Resolution using Stable Diffusion Model
Omnidirectional images (ODIs) are commonly used in real-world visual tasks, and high-resolution ODIs help improve the performance of related visual tasks.
Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation
To fully utilize the information within the intermediate domain, we propose a symmetric Guidance training strategy (SymGD), which additionally offers direct guidance to unlabeled data by merging pseudo labels from intermediate samples.
BG-YOLO: A Bidirectional-Guided Method for Underwater Object Detection
When training the enhancement branch, the object detection subnet in the enhancement branch guides the image enhancement subnet to be optimized towards the direction that is most conducive to the detection task.
Automated Polyp Segmentation in Colonoscopy Images
The combination of dilated convolution module, RCCA, and global average pooling was found to be effective for irregular shapes.
Mirror-3DGS: Incorporating Mirror Reflections into 3D Gaussian Splatting
3D Gaussian Splatting (3DGS) has marked a significant breakthrough in the realm of 3D scene reconstruction and novel view synthesis.
InstantSplat: Unbounded Sparse-view Pose-free Gaussian Splatting in 40 Seconds
This pre-processing is usually conducted via a Structure-from-Motion (SfM) pipeline, a procedure that can be slow and unreliable, particularly in sparse-view scenarios with insufficient matched features for accurate reconstruction.
Invertible Diffusion Models for Compressed Sensing
To enable such memory-intensive end-to-end finetuning, we propose a novel two-level invertible design to transform both (1) the multi-step sampling process and (2) the noise estimation U-Net in each step into invertible networks.
BadEdit: Backdooring large language models by model editing
It boasts superiority over existing backdoor injection techniques in several areas: (1) Practicality: BadEdit necessitates only a minimal dataset for injection (15 samples).
Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model
Universal image restoration is a practical and potential computer vision task for real-world applications.
MamMIL: Multiple Instance Learning for Whole Slide Images with State Space Models
To tackle this challenge, we propose a MamMIL framework for WSI classification by cooperating the selective structured state space model (i. e., Mamba) with MIL for the first time, enabling the modeling of instance dependencies while maintaining linear complexity.
Region-Transformer: Self-Attention Region Based Class-Agnostic Point Cloud Segmentation
Attention-based networks have succeeded in many previous methods of performing point cloud segmentation.
Are Large Language Models Rational Investors?
Large Language Models (LLMs) are progressively being adopted in financial analysis to harness their extensive knowledge base for interpreting complex market data and trends.
NetInfoF Framework: Measuring and Exploiting Network Usable Information
Given a node-attributed graph, and a graph task (link prediction or node classification), can we tell if a graph neural network (GNN) will perform well?
DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing
Large-scale Text-to-Image (T2I) diffusion models have revolutionized image generation over the last few years.
Efficient Non-Parametric Uncertainty Quantification for Black-Box Large Language Models and Decision Planning
This paper focuses on decision planning with uncertainty estimation to address the hallucination problem in language models.
360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model
Recently, the emerging text-to-video (T2V) diffusion methods demonstrate notable effectiveness in standard video generation.
Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy
This survey comprehensively examines the emerging field of AIGC-based Brain-conditional Multimodal Synthesis, termed AIGC-Brain, to delineate the current landscape and future directions.
A Prompt Learning Framework for Source Code Summarization
PromptCS trains a prompt agent that can generate continuous prompts to unleash the potential for LLMs in code summarization.
Language-Assisted 3D Scene Understanding
The scale and quality of point cloud datasets constrain the advancement of point cloud learning.
Neural Video Fields Editing
Specifically, we construct a neural video field, powered by tri-plane and sparse grid, to enable encoding long videos with hundreds of frames in a memory-efficient manner.
EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection
In the era where AI-generated content (AIGC) models can produce stunning and lifelike images, the lingering shadow of unauthorized reproductions and malicious tampering poses imminent threats to copyright integrity and information security.
GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization
This paper presents GIR, a 3D Gaussian Inverse Rendering method for relightable scene factorization.
PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction
To make up for the lack of dynamic HOI scenarios in this area, we introduce the BallPlay dataset that contains eight whole-body basketball skills.
AnimateZero: Video Diffusion Models are Zero-Shot Image Animators
For appearance control, we borrow intermediate latents and their features from the text-to-image (T2I) generation for ensuring the generated first frame is equal to the given generated image.
SecureCut: Federated Gradient Boosting Decision Trees with Efficient Machine Unlearning
In response to legislation mandating companies to honor the \textit{right to be forgotten} by erasing user data, it has become imperative to enable data removal in Vertical Federated Learning (VFL) where multiple parties provide private features for model training.
Generative Structural Design Integrating BIM and Diffusion Model
This study proposes a comprehensive solution.
Constructing Sample-to-Class Graph for Few-Shot Class-Incremental Learning
Moreover, we design a multi-stage strategy for training S2C model, which mitigates the training challenges posed by limited data in the incremental process.
Multilevel Perception Boundary-guided Network for Breast Lesion Segmentation in Ultrasound Images
Moreover, to improve the segmentation performance for tumor boundaries, a multi-level boundary-enhanced segmentation (BS) loss is proposed.
Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts
Recent text-to-3D generation methods achieve impressive 3D content creation capacity thanks to the advances in image diffusion models and optimizing strategies.
Compatible Transformer for Irregularly Sampled Multivariate Time Series
To analyze multivariate time series, most previous methods assume regular subsampling of time series, where the interval between adjacent measurements and the number of samples remain unchanged.
Deep Unfolding Network for Image Compressed Sensing by Content-adaptive Gradient Updating and Deformation-invariant Non-local Modeling
In this paper, inspired by the traditional Proximal Gradient Descent (PGD) algorithm, a novel DUN for image compressed sensing (dubbed DUN-CSNet) is proposed to solve the above two issues.
Empirical Study of Zero-Shot NER with ChatGPT
Large language models (LLMs) exhibited powerful capability in various natural language processing tasks.
Multimodal Large Language Model for Visual Navigation
Recent efforts to enable visual navigation using large language models have mainly focused on developing complex prompt systems.
SSPFusion: A Semantic Structure-Preserving Approach for Infrared and Visible Image Fusion
Most existing learning-based infrared and visible image fusion (IVIF) methods exhibit massive redundant information in the fusion images, i. e., yielding edge-blurring effect or unrecognizable for object detectors.
IAIFNet: An Illumination-Aware Infrared and Visible Image Fusion Network
Infrared and visible image fusion (IVIF) is used to generate fusion images with comprehensive features of both images, which is beneficial for downstream vision tasks.
TextCLIP: Text-Guided Face Image Generation And Manipulation Without Adversarial Training
Text-guided image generation aimed to generate desired images conditioned on given texts, while text-guided image manipulation refers to semantically edit parts of a given image based on specified texts.
Exploring Flat Minima for Domain Generalization with Large Learning Rates
Instead, we observe that leveraging a large learning rate can simultaneously promote weight diversity and facilitate the identification of flat regions in the loss landscape.
sasdim: self-adaptive noise scaling diffusion model for spatial time series imputation
Spatial time series imputation is critically important to many real applications such as intelligent transportation and air quality monitoring.
Self-Supervised Scalable Deep Compressed Sensing
Compressed sensing (CS) is a promising tool for reducing sampling costs.
Masked Cross-image Encoding for Few-shot Segmentation
Few-shot segmentation (FSS) is a dense prediction task that aims to infer the pixel-wise labels of unseen classes using only a limited number of annotated images.
Ranked #24 on
Few-Shot Semantic Segmentation
on COCO-20i (5-shot)
DomainAdaptor: A Novel Approach to Test-time Adaptation
To deal with the domain shift between training and test samples, current methods have primarily focused on learning generalizable features during training and ignore the specificity of unseen samples that are also critical during the test.
DiffLLE: Diffusion-guided Domain Calibration for Unsupervised Low-light Image Enhancement
Specifically, we adopt a naive unsupervised enhancement algorithm to realize preliminary restoration and design two zero-shot plug-and-play modules based on diffusion model to improve generalization and effectiveness.
Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization
Domain generalization (DG) is proposed to deal with the issue of domain shift, which occurs when statistical differences exist between source and target domains.
EFLNet: Enhancing Feature Learning for Infrared Small Target Detection
To address this problem, we propose a new adaptive threshold focal loss (ATFL) function that decouples the target and the background, and utilizes the adaptive mechanism to adjust the loss weight to force the model to allocate more attention to target features.
Deep Physics-Guided Unrolling Generalization for Compressed Sensing
By absorbing the merits of both the model- and data-driven methods, deep physics-engaged learning scheme achieves high-accuracy and interpretable image reconstruction.
PKU-GoodsAD: A Supermarket Goods Dataset for Unsupervised Anomaly Detection and Segmentation
It follows the unsupervised setting and only normal (defect-free) images are used for training.
DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models
Specifically, we construct classifier guidance based on the strong correspondence of intermediate features in the diffusion model.
HVTSurv: Hierarchical Vision Transformer for Patient-Level Survival Prediction from Whole Slide Image
Many studies adopt random sampling pre-processing strategy and WSI-level aggregation models, which inevitably lose critical prognostic information in the patient-level bag.
Dynamic Path-Controllable Deep Unfolding Network for Compressive Sensing
Deep unfolding network (DUN) that unfolds the optimization algorithm into a deep neural network has achieved great success in compressive sensing (CS) due to its good interpretability and high performance.
Infrastructure Crack Segmentation: Boundary Guidance Method and Benchmark Dataset
Cracks provide an essential indicator of infrastructure performance degradation, and achieving high-precision pixel-level crack segmentation is an issue of concern.
On the Tool Manipulation Capability of Open-source Large Language Models
In this paper, we ask can we enhance open-source LLMs to be competitive to leading closed LLM APIs in tool manipulation, with practical amount of human supervision.
Cross-source Point Cloud Registration: Challenges, Progress and Prospects
The emerging topic of cross-source point cloud (CSPC) registration has attracted increasing attention with the fast development background of 3D sensor technologies.
An Object SLAM Framework for Association, Mapping, and High-Level Tasks
Taking into consideration the semantic invariance of objects, we convert the object map to a topological map to provide semantic descriptors to enable multi-map matching.
Single Node Injection Label Specificity Attack on Graph Neural Networks via Reinforcement Learning
Furthermore, most methods concentrate on a single attack goal and lack a generalizable adversary to develop distinct attack strategies for diverse goals, thus limiting precise control over victim model behavior in real-world scenarios.
Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention
We evaluate our model on various dialogue understanding tasks including dialogue relation extraction, dialogue emotion recognition, and dialogue act classification.
Ranked #1 on
Dialog Relation Extraction
on DialogRE
Optimization-Inspired Cross-Attention Transformer for Compressive Sensing
And, PGCA block achieves an enhanced information interaction, which introduces the inertia force into the gradient descent step through a cross attention block.
OPDN: Omnidirectional Position-aware Deformable Network for Omnidirectional Image Super-Resolution
Model A aims to enhance the feature extraction ability of 360{\deg} image positional information, while Model B further focuses on the high-frequency information of 360{\deg} images.
Large-capacity and Flexible Video Steganography via Invertible Neural Network
For large-capacity, we present a reversible pipeline to perform multiple videos hiding and recovering through a single invertible neural network (INN).
Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration
Deep point cloud registration methods face challenges to partial overlaps and rely on labeled data.
Implicit Neural Representation for Cooperative Low-light Image Enhancement
Finally, extensive experiments demonstrate the robustness and superior effectiveness of our proposed NeRCo.
Progressive Content-aware Coded Hyperspectral Compressive Imaging
Hyperspectral imaging plays a pivotal role in a wide range of applications, like remote sensing, medicine, and cytology.
A Unified Continual Learning Framework with General Parameter-Efficient Tuning
1) Learning: the pre-trained model adapts to the new task by tuning an online PET module, along with our adaptation speed calibration to align different PET modules, 2) Accumulation: the task-specific knowledge learned by the online PET module is accumulated into an offline PET module through momentum update, 3) Ensemble: During inference, we respectively construct two experts with online/offline PET modules (which are favored by the novel/historical tasks) for prediction ensemble.
FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model
In this work, we propose a training-Free conditional Diffusion Model (FreeDoM) used for various conditions.
Unlimited-Size Diffusion Restoration
Our simple, parameter-free approaches can be used not only for image restoration but also for image generation of unlimited sizes, with the potential to be a general tool for diffusion models.
T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models
In this paper, we aim to ``dig out" the capabilities that T2I models have implicitly learned, and then explicitly use them to control the generation more granularly.
Cross-domain recommendation via user interest alignment
Specifically, we first construct a unified cross-domain heterogeneous graph and redefine the message passing mechanism of graph convolutional networks to capture high-order similarity of users and items across domains.
Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text
(2) How to enhance the perception of reasoning types for the models?
Temporal-Coded Spiking Neural Networks with Dynamic Firing Threshold: Learning with Event-Driven Backpropagation
As a temporal encoding scheme for SNNs, Time-To-First-Spike (TTFS) encodes information using the timing of a single spike, which allows spiking neurons to transmit information through sparse spike trains and results in lower power consumption and higher computational efficiency compared to traditional rate-based encoding counterparts.
Panoptic Compositional Feature Field for Editable Scene Rendering With Network-Inferred Labels via Metric Learning
In this work, we attempt to learn an object-compositional neural implicit representation for editable scene rendering by leveraging labels inferred from the off-the-shelf 2D panoptic segmentation networks instead of the ground truth annotations.
Latent Evolution Model for Change Point Detection in Time-varying Networks
Our method focuses on learning the low-dimensional representations of networks and capturing the evolving patterns of these learned latent representations simultaneously.
Position Embedding Needs an Independent Layer Normalization
By analyzing the input and output of each encoder layer in VTs using reparameterization and visualization, we find that the default PE joining method (simply adding the PE and patch embedding together) operates the same affine transformation to token embedding and PE, which limits the expressiveness of PE and hence constrains the performance of VTs.
Self-Supervised Object Goal Navigation with In-Situ Finetuning
In contrast, our LocCon shows the most robust transfer in the real world among the set of models we compare to, and that the real-world performance of all models can be further improved with self-supervised LocCon in-situ training.
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
Most existing Image Restoration (IR) models are task-specific, which can not be generalized to different degradation operators.
Ranked #1 on
Image Compressed Sensing
on CelebA
GAN Prior based Null-Space Learning for Consistent Super-Resolution
Consistency and realness have always been the two critical issues of image super-resolution.
Complementary Labels Learning with Augmented Classes
In this paper, we propose a novel problem setting called Complementary Labels Learning with Augmented Classes (CLLAC), which brings the challenge that classifiers trained by complementary labels should not only be able to classify the instances from observed classes accurately, but also recognize the instance from the Augmented Classes in the testing phase.
Masked Vision-Language Transformers for Scene Text Recognition
MVLT is trained in two stages: in the first stage, we design a STR-tailored pretraining method based on a masking strategy; in the second stage, we fine-tune our model and adopt an iterative correction method to improve the performance.
Overlap-guided Gaussian Mixture Models for Point Cloud Registration
Probabilistic 3D point cloud registration methods have shown competitive performance in overcoming noise, outliers, and density variations.
Multi-Agent Automated Machine Learning
In this paper, we propose multi-agent automated machine learning (MA2ML) with the aim to effectively handle joint optimization of modules in automated machine learning (AutoML).
Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding
Unsupervised learning on 3D point clouds has undergone a rapid evolution, especially thanks to data augmentation-based contrastive methods.
Towards Multimodal Multitask Scene Understanding Models for Indoor Mobile Agents
The perception system in personalized mobile agents requires developing indoor scene understanding models, which can understand 3D geometries, capture objectiveness, analyze human behaviors, etc.
SAFER: Safe Collision Avoidance using Focused and Efficient Trajectory Search with Reinforcement Learning
Collision avoidance is key for mobile robots and agents to operate safely in the real world.
D3C2-Net: Dual-Domain Deep Convolutional Coding Network for Compressive Sensing
By unfolding the proposed framework into deep neural networks, we further design a novel Dual-Domain Deep Convolutional Coding Network (D3C2-Net) for CS imaging with the capability of transmitting high-throughput feature-level image representation through all the unfolded stages.
TransCL: Transformer Makes Strong and Flexible Compressive Learning
Compressive learning (CL) is an emerging framework that integrates signal acquisition via compressed sensing (CS) and machine learning for inference tasks directly on a small number of measurements.
Spatial-temporal Analysis for Automated Concrete Workability Estimation
Concrete workability measure is mostly determined based on subjective assessment of a certified assessor with visual inspections.
Content-aware Scalable Deep Compressed Sensing
To more efficiently address image compressed sensing (CS) problems, we present a novel content-aware scalable network dubbed CASNet which collectively achieves adaptive sampling rate allocation, fine granular scalability and high-quality reconstruction.
Ranked #1 on
Image Compressed Sensing
on CBSD68
Frequency Domain Model Augmentation for Adversarial Attack
Specifically, we apply a spectrum transformation to the input and thus perform the model augmentation in the frequency domain.
Self-attention on Multi-Shifted Windows for Scene Segmentation
Scene segmentation in images is a fundamental yet challenging problem in visual content understanding, which is to learn a model to assign every image pixel to a categorical label.
Horizontal and Vertical Attention in Transformers
Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies.
Measuring and Improving the Use of Graph Information in Graph Neural Networks
Graph neural networks (GNNs) have been widely used for representation learning on graph data.
Multiple Instance Learning with Mixed Supervision in Gleason Grading
We achieve the state-of-the-art performance on the SICAPv2 dataset, and the visual analysis shows the accurate prediction results of instance level.
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.
Eco-driving for Electric Connected Vehicles at Signalized Intersections: A Parameterized Reinforcement Learning approach
This paper proposes an eco-driving framework for electric connected vehicles (CVs) based on reinforcement learning (RL) to improve vehicle energy efficiency at signalized intersections.
Using EBGAN for Anomaly Intrusion Detection
The generator in IDS-EBGAN is responsible for converting the original malicious network traffic in the training set into adversarial malicious examples.
Hierarchical Similarity Learning for Aliasing Suppression Image Super-Resolution
As a highly ill-posed issue, single image super-resolution (SISR) has been widely investigated in recent years.
Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation
Neural Radiance Fields (NeRF) have emerged as a potent paradigm for representing scenes and synthesizing photo-realistic images.
MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolution
Instead of using known degradation levels as explicit supervision to the interactive mechanism, we propose a metric learning strategy to map the unquantifiable degradation levels in real-world scenarios to a metric space, which is trained in an unsupervised manner.
Deep Generalized Unfolding Networks for Image Restoration
Concretely, without loss of interpretability, we integrate a gradient estimation strategy into the gradient descent step of the Proximal Gradient Descent (PGD) algorithm, driving it to deal with complex and real-world image degradation.
Learning Weighting Map for Bit-Depth Expansion within a Rational Range
Existing BDE methods have no unified solution for various BDE situations, and directly learn a mapping for each pixel from LBD image to the desired value in HBD image, which may change the given high-order bits and lead to a huge deviation from the ground truth.
Investigating Accuracy-Novelty Performance for Graph-based Collaborative Filtering
While conventional CF models are known for facing the challenges of the popularity bias that favors popular items, one may wonder "Whether the existing graph-based CF models alleviate or exacerbate popularity bias of recommender systems?"
PUERT: Probabilistic Under-sampling and Explicable Reconstruction Network for CS-MRI
Compressed Sensing MRI (CS-MRI) aims at reconstructing de-aliased images from sub-Nyquist sampling k-space data to accelerate MR Imaging, thus presenting two basic issues, i. e., where to sample and how to reconstruct.
R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning
After RRL, the classification head is refined with global class-balanced classification loss to address the data imbalance issue as well as learn the decision boundaries between new and previous classes.
A Prompting-based Approach for Adversarial Example Generation and Robustness Enhancement
Our attack technique targets the inherent vulnerabilities of NLP models, allowing us to generate samples even without interacting with the victim NLP model, as long as it is based on pre-trained language models (PLMs).
Series Photo Selection via Multi-view Graph Learning
Series photo selection (SPS) is an important branch of the image aesthetics quality assessment, which focuses on finding the best one from a series of nearly identical photos.
Panini-Net: GAN Prior Based Degradation-Aware Feature Interpolation for Face Restoration
Emerging high-quality face restoration (FR) methods often utilize pre-trained GAN models (\textit{i. e.}, StyleGAN2) as GAN Prior.
NeRFocus: Neural Radiance Field for 3D Synthetic Defocus
Unlike the pinhole, the thin lens refracts rays of a scene point, so its imaging on the sensor plane is scattered as a circle of confusion (CoC).
Unsupervised Learning on 3D Point Clouds by Clustering and Contrasting
This paper proposes a general unsupervised approach, named \textbf{ConClu}, to perform the learning of point-wise and global features by jointly leveraging point-level clustering and instance-level contrasting.
Quantifying Robustness to Adversarial Word Substitutions
Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations.
Image Disentanglement Autoencoder for Steganography Without Embedding
Conventional steganography approaches embed a secret message into a carrier for concealed communication but are prone to attack by recent advanced steganalysis tools.
Robust Invertible Image Steganography
Previous image steganography methods are limited in hiding capacity and robustness, commonly vulnerable to distortion on container images such as Gaussian noise, Poisson noise, and lossy compression.
CSformer: Bridging Convolution and Transformer for Compressive Sensing
The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery.
COTReg:Coupled Optimal Transport based Point Cloud Registration
Generating a set of high-quality correspondences or matches is one of the most critical steps in point cloud registration.
MVDG: A Unified Multi-view Framework for Domain Generalization
Beyond the training stage, overfitting could also cause unstable prediction in the test stage.
HerosNet: Hyperspectral Explicable Reconstruction and Optimal Sampling Deep Network for Snapshot Compressive Imaging
Hyperspectral imaging is an essential imaging modality for a wide range of applications, especially in remote sensing, agriculture, and medicine.
GenReg: Deep Generative Method for Fast Point Cloud Registration
To solve this challenge, we propose a new data-driven registration algorithm by investigating deep generative neural networks to point cloud registration.
Can Graph Neural Networks Learn to Solve MaxSAT Problem?
With the rapid development of deep learning techniques, various recent work has tried to apply graph neural networks (GNNs) to solve NP-hard problems such as Boolean Satisfiability (SAT), which shows the potential in bridging the gap between machine learning and symbolic reasoning.
ε-weakened Robustness of Deep Neural Networks
This paper introduces a notation of $\varepsilon$-weakened robustness for analyzing the reliability and stability of deep neural networks (DNNs).
Research on the Inverse Kinematics Prediction of a Soft Biomimetic Actuator via BP Neural Network
After training with sample data, the BP neural network model can represent the relation between the manipulator tip position and the pressure applied to the chambers.
Memory-Augmented Deep Unfolding Network for Compressive Sensing
By understanding DUNs from the perspective of the human brain's memory processing, we find there exists two issues in existing DUNs.
Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentation
In semi-supervised medical image segmentation, most previous works draw on the common assumption that higher entropy means higher uncertainty.
Dyn-Backdoor: Backdoor Attack on Dynamic Link Prediction
Backdoor attacks induce the DLP methods to make wrong prediction by the malicious training data, i. e., generating a subgraph sequence as the trigger and embedding it to the training data.
Serving DNN Models with Multi-Instance GPUs: A Case of the Reconfigurable Machine Scheduling Problem
With MIG, A100 can be the most cost-efficient GPU ever for serving Deep Neural Networks (DNNs).
Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imaging
To better exploit the spatial-temporal correlation among frames and address the problem of information loss between adjacent phases in existing DUNs, we propose to adopt the 3D-CNN prior in our proximal mapping module and develop a novel dense feature map (DFM) strategy, respectively.
Dynamic Attentive Graph Learning for Image Restoration
Specifically, we propose an improved graph model to perform patch-wise graph convolution with a dynamic and adaptive number of neighbors for each node.
Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach
Learning from the web can ease the extreme dependence of deep learning on large-scale manually labeled datasets.
Structure Destruction and Content Combination for Face Anti-Spoofing
In pursuit of consolidating the face verification systems, prior face anti-spoofing studies excavate the hidden cues in original images to discriminate real persons and diverse attack types with the assistance of auxiliary supervision.
EGC2: Enhanced Graph Classification with Easy Graph Compression
To achieve lower-complexity defense applied to graph classification models, EGC2 utilizes a centrality-based edge-importance index to compress the graphs, filtering out trivial structures and adversarial perturbations in the input graphs, thus improving the model's robustness.
Multi-Level Contrastive Learning for Few-Shot Problems
Most current applications of contrastive learning benefit only a single representation from the last layer of an encoder. In this paper, we propose a multi-level contrasitive learning approach which applies contrastive losses at different layers of an encoder to learn multiple representations from the encoder.
COAST: COntrollable Arbitrary-Sampling NeTwork for Compressive Sensing
In this paper, we propose a novel COntrollable Arbitrary-Sampling neTwork, dubbed COAST, to solve CS problems of arbitrary-sampling matrices (including unseen sampling matrices) with one single model.
Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification
To better eliminate interference from occlusions, we design a contrast feature learning technique (CFL) for better separation of occlusion features and discriminative ID features.
Spk2ImgNet: Learning To Reconstruct Dynamic Scene From Continuous Spike Stream
Different from the conventional digital cameras that compact the photoelectric information within the exposure interval into a single snapshot, the spike camera produces a continuous spike stream to record the dynamic light intensity variation process.
TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification
Multiple instance learning (MIL) is a powerful tool to solve the weakly supervised classification in whole slide image (WSI) based pathology diagnosis.
A Multi-Branch Hybrid Transformer Networkfor Corneal Endothelial Cell Segmentation
Corneal endothelial cell segmentation plays a vital role inquantifying clinical indicators such as cell density, coefficient of variation, and hexagonality.
Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching
This paper proposes an approach to Dense Video Captioning (DVC) without pairwise event-sentence annotation.
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration.
Unsupervised Sentiment Analysis by Transferring Multi-source Knowledge
The first mechanism is a selective domain adaptation (SDA) method, which transfers knowledge from the closest source domain.
Underwater Target Recognition based on Multi-Decision LOFAR Spectrum Enhancement: A Deep Learning Approach
To overcome this issue and to further improve the recognition performance, we adopt a deep learning approach for underwater target recognition and propose a LOFAR spectrum enhancement (LSE)-based underwater target recognition scheme, which consists of preprocessing, offline training, and online testing.
Super-Resolving Compressed Video in Coding Chain
Scaling and lossy coding are widely used in video transmission and storage.
Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation
To further mine the non-salient region objects, we propose to exert the segmentation network's self-correction ability.
Jo-SRC: A Contrastive Approach for Combating Noisy Labels
Due to the memorization effect in Deep Neural Networks (DNNs), training with noisy labels usually results in inferior model performance.
ISTA-Net++: Flexible Deep Unfolding Network for Compressive Sensing
While deep neural networks have achieved impressive success in image compressive sensing (CS), most of them lack flexibility when dealing with multi-ratio tasks and multi-scene images in practical applications.
Thousand to One: Semantic Prior Modeling for Conceptual Coding
To this end, we propose a novel end-to-end semantic prior modeling-based conceptual coding scheme towards extremely low bitrate image compression, which leverages semantic-wise deep representations as a unified prior for entropy estimation and texture synthesis.
COLA-Net: Collaborative Attention Network for Image Restoration
Local and non-local attention-based methods have been well studied in various image restoration tasks while leading to promising performance.
A comprehensive survey on point cloud registration
This survey conducts a comprehensive survey, including both same-source and cross-source registration methods, and summarize the connections between optimization-based and deep learning methods, to provide further research insight.
Temperature dependent coherence properties of NV ensemble in diamond up to 600K
Nitrogen-vacancy (NV) center in diamond is an ideal candidate for quantum sensors because of its excellent optical and coherence property.
Quantum Physics Mesoscale and Nanoscale Physics
Semantically Meaningful Class Prototype Learning for One-Shot Image Semantic Segmentation
Then we utilize the fused prototype to guide the final segmentation of the query image.
Temporal-Amount Snapshot MultiGraph for Ethereum Transaction Tracking
With the wide application of blockchain in the financial field, the rise of various types of cybercrimes has brought great challenges to the security of blockchain.
Aurora Guard: Reliable Face Anti-Spoofing via Mobile Lighting System
Face authentication on mobile end has been widely applied in various scenarios.
Exploiting Web Images for Fine-Grained Visual Recognition by Eliminating Noisy Samples and Utilizing Hard Ones
Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators.
Uncertainty Weighted Offline Reinforcement Learning
Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration.
Multi-Representation Ensemble in Few-Shot Learning
Deep neural networks (DNNs) compute representations in a layer by layer fashion, producing a final representation at the top layer of the pipeline, and classification or regression is made using the final representation.
Super Resolve Dynamic Scene From Continuous Spike Streams
In this paper, we properly exploit the relative motion and derive the relationship between light intensity and each spike, so as to recover the external scene with both high temporal and high spatial resolution.
Revisiting BFfloat16 Training
We ask can we do pure 16-bit training which requires only 16-bit compute units, while still matching the model accuracy attained by 32-bit training.
Counting the Number of Solutions to Constraints
Compared with constraint satisfaction problems, counting problems have received less attention.
Multiple Instance Segmentation in Brachial Plexus Ultrasound Image Using BPMSegNet
In this paper, a network called Brachial Plexus Multi-instance Segmentation Network (BPMSegNet) is proposed to identify different tissues (nerves, arteries, veins, muscles) in ultrasound images.
PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning
Second, the extra unlabeled samples are employed to transfer the knowledge from base classes to novel classes through contrastive learning.
Self-Supervised Learning of Lidar Segmentation for Autonomous Indoor Navigation
We provide insights into our network predictions and show that our approach can also improve the performances of common localization techniques.
Rigid and Articulated Point Registration with Expectation Conditional Maximization
This paper addresses the issue of matching rigid and articulated shapes through probabilistic point registration.
Field-wise Learning for Multi-field Categorical Data
We present a model that utilizes linear models with variance and low-rank constraints, to help it generalize better and reduce the number of parameters.
Time-Series Snapshot Network for Partner Recommendation: A Case Study on OSS
In this paper, we introduce time-series snapshot network (TSSN) which is a mixture network to model the interactions among users and developers.
Social and Information Networks
Conceptual Compression via Deep Structure and Texture Synthesis
To this end, we propose a novel conceptual compression framework that encodes visual data into compact structure and texture representations, then decodes in a deep synthesis fashion, aiming to achieve better visual reconstruction quality, flexible content manipulation, and potential support for various vision tasks.
Multi-layer Feature Aggregation for Deep Scene Parsing Models
The proposed module can auto-select the intermediate visual features to correlate the spatial and semantic information.
Ranked #47 on
Semantic Segmentation
on NYU Depth v2
Distribution-aware Margin Calibration for Medical Image Segmentation
In this paper, we present a novel data-distribution-aware margin calibration method for a better generalization of the mIoU over the whole data-distribution, underpinned by a rigid lower bound.
Parameter Efficient Deep Neural Networks with Bilinear Projections
Recent research on deep neural networks (DNNs) has primarily focused on improving the model accuracy.
Dual Attention on Pyramid Feature Maps for Image Captioning
In this paper, we propose to apply dual attention on pyramid image feature maps to fully explore the visual-semantic correlations and improve the quality of generated sentences.
AutoBSS: An Efficient Algorithm for Block Stacking Style Search
Neural network architecture design mostly focuses on the new convolutional operator or special topological structure of network block, little attention is drawn to the configuration of stacking each block, called Block Stacking Style (BSS).
Identification of deep breath while moving forward based on multiple body regions and graph signal analysis
This paper presents an unobtrusive solution that can automatically identify deep breath when a person is walking past the global depth camera.
Revisiting BFloat16 Training
State-of-the-art generic low-precision training algorithms use a mix of 16-bit and 32-bit precision, creating the folklore that 16-bit hardware compute units alone are not enough to maximize model accuracy.
Face Mask Assistant: Detection of Face Mask Service Stage Based on Mobile Phone
Aimed at solving the problem that we don't know which service stage of the mask belongs to, we propose a detection system based on the mobile phone.
ASDN: A Deep Convolutional Network for Arbitrary Scale Image Super-Resolution
For SR of small-scales (between 1 and 2), images are constructed by interpolation from a sparse set of precalculated Laplacian pyramid levels.
Scalar Coupling Constant Prediction Using Graph Embedding Local Attention Encoder
The experimental results demonstrate that, compared to the traditional chemical bond structure representations, the rotation and translation invariant structure representations proposed in this work can improve the SCC prediction accuracy; with the graph embedded local self-attention, the mean absolute error (MAE) of the prediction model in the validation set decreases from 0. 1603 Hz to 0. 1067 Hz; using the classification based loss function instead of the scaled regression loss, the MAE of the predicted SCC can be decreased to 0. 0963 HZ, which is close to the quantum chemistry standard on CHAMPS dataset.
Implicit Multidimensional Projection of Local Subspaces
We propose a visualization method to understand the effect of multidimensional projection on local subspaces, using implicit function differentiation.
Computational prediction of RNA tertiary structures using machine learning methods
RNAs play crucial and versatile roles in biological processes.
Face Anti-Spoofing Via Disentangled Representation Learning
Face anti-spoofing is crucial to security of face recognition systems.
Salvage Reusable Samples from Noisy Data for Robust Learning
To this end, we propose a certainty-based reusable sample selection and correction approach, termed as CRSSC, for coping with label noise in training deep FG models with web images.
Hardware Accelerator for Adversarial Attacks on Deep Learning Neural Networks
Recent studies identify that Deep learning Neural Networks (DNNs) are vulnerable to subtle perturbations, which are not perceptible to human visual system but can fool the DNN models and lead to wrong outputs.
MACD R-CNN: An Abnormal Cell Nucleus Detection Method
We design a fixed proposal module to generate fixed-sized feature maps of nuclei, which allows the new information of nucleus is used for classification.
A Similarity Inference Metric for RGB-Infrared Cross-Modality Person Re-identification
RGB-Infrared (IR) cross-modality person re-identification (re-ID), which aims to search an IR image in RGB gallery or vice versa, is a challenging task due to the large discrepancy between IR and RGB modalities.
Cross-Modality Person Re-identification
Person Re-Identification
Stochastic Batch Augmentation with An Effective Distilled Dynamic Soft Label Regularizer
SBA stochastically decides whether to augment at iterations controlled by the batch scheduler and in which a ''distilled'' dynamic soft label regularization is introduced by incorporating the similarity in the vicinity distribution respect to raw samples.
Automated Radiological Report Generation For Chest X-Rays With Weakly-Supervised End-to-End Deep Learning
The model provides automated recognition of given scans and generation of reports.
Understanding Graph Neural Networks from Graph Signal Denoising Perspectives
This paper aims to provide a theoretical framework to understand GNNs, specifically, spectral graph convolutional networks and graph attention networks, from graph signal denoising perspectives.
TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples
The challenges of high intra-class variance yet low inter-class fluctuations in fine-grained visual categorization are more severe with few labeled samples, \textit{i. e.,} Fine-Grained categorization problems under the Few-Shot setting (FGFS).
Iterative Network for Image Super-Resolution
A novel iterative super-resolution network (ISRN) is proposed on top of the iterative optimization.
Contextual Embeddings: When Are They Worth It?
We study the settings for which deep contextual embeddings (e. g., BERT) give large improvements in performance relative to classic pretrained embeddings (e. g., GloVe), and an even simpler baseline---random word embeddings---focusing on the impact of the training set size and the linguistic properties of the task.
Towards Better Graph Representation: Two-Branch Collaborative Graph Neural Networks for Multimodal Marketing Intention Detection
Inspired by the fact that spreading and collecting information through the Internet becomes the norm, more and more people choose to post for-profit contents (images and texts) in social networks.
Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences
We present a fast feature-metric point cloud registration framework, which enforces the optimisation of registration by minimising a feature-metric projection error without correspondences.
DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks
On one hand, we can reduce the computation cost remarkably while maintaining the performance.
Generalizable Model-agnostic Semantic Segmentation via Target-specific Normalization
Semantic segmentation in a supervised learning manner has achieved significant progress in recent years.
GID-Net: Detecting Human-Object Interaction with Global and Instance Dependency
GID block breaks through the local neighborhoods and captures long-range dependency of pixels both in global-level and instance-level from the scene to help detecting interactions between instances.
Understanding the Downstream Instability of Word Embeddings
To theoretically explain this tradeoff, we introduce a new measure of embedding instability---the eigenspace instability measure---which we prove bounds the disagreement in downstream predictions introduced by the change in word embeddings.
Multi-factorial Optimization for Large-scale Virtual Machine Placement in Cloud Computing
However, as growing demand for cloud services, the existing EAs fail to implement in large-scale virtual machine placement (LVMP) problem due to the high time complexity and poor scalability.
PMC-GANs: Generating Multi-Scale High-Quality Pedestrian with Multimodal Cascaded GANs
Recently, generative adversarial networks (GANs) have shown great advantages in synthesizing images, leading to a boost of explorations of using faked images to augment data.
Adversarial AutoAugment
The augmentation policy network attempts to increase the training loss of a target network through generating adversarial augmentation policies, while the target network can learn more robust features from harder examples to improve the generalization.
Ranked #594 on
Image Classification
on ImageNet
Relational Mimic for Visual Adversarial Imitation Learning
In this work, we introduce a new method for imitation learning from video demonstrations.
Potential Passenger Flow Prediction: A Novel Study for Urban Transportation Development
In this paper, this specific problem is termed as potential passenger flow (PPF) prediction, which is a novel and important study connected with urban computing and intelligent transportation systems.
Adversarial Domain Adaptation with Domain Mixup
In this paper, we present adversarial domain adaptation with domain mixup (DM-ADA), which guarantees domain-invariance in a more continuous latent space and guides the domain discriminator in judging samples' difference relative to source and target domains.
Time-aware Gradient Attack on Dynamic Network Link Prediction
In this work, we present the first study of adversarial attack on dynamic network link prediction (DNLP).
