Search Results for author:
Found 280 papers, 99 papers with code
Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark
In this work, we analyze the entries from DAWNBench, which received optimized submissions from multiple industrial groups, to investigate the behavior of TTA as a metric as well as trends in the best-performing entries.
Feature Affinity based Pseudo Labeling for Semi-supervised Person Re-identification
Our approach measures the affinity of unlabeled samples with the underlying clusters of labeled data samples using the intermediate feature representations from deep networks.
Globally Variance-Constrained Sparse Representation and Its Application in Image Set Coding
Therefore, introducing an accurate rate-constraint in sparse coding and dictionary learning becomes meaningful, which has not been fully exploited in the context of sparse representation.
Global Pose Estimation with an Attention-based Recurrent Network
The ability for an agent to localize itself within an environment is crucial for many real-world applications.
Deep Reinforcement Learning for Image Hashing
Inspired by the sequential decision ability of deep reinforcement learning, we propose a new Deep Reinforcement Learning approach for Image Hashing (DRLIH).
SCH-GAN: Semi-supervised Cross-modal Hashing by Generative Adversarial Network
(2) Ignore the rich information contained in the large amount of unlabeled data across different modalities, especially the margin examples that are easily to be incorrectly retrieved, which can help to model the correlations.
Multi-pseudo Regularized Label for Generated Data in Person Re-Identification
Unlike the traditional label which usually is a single integral number, the virtual label proposed in this work is a set of weight-based values each individual of which is a number in (0, 1] called multi-pseudo label and reflects the degree of relation between each generated data to every pre-defined class of real data.
Unsupervised Generative Adversarial Cross-modal Hashing
To address the above problem, in this paper we propose an Unsupervised Generative Adversarial Cross-modal Hashing approach (UGACH), which makes full use of GAN's ability for unsupervised representation learning to exploit the underlying manifold structure of cross-modal data.
Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards
Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge.
Kill Two Birds with One Stone: Weakly-Supervised Neural Network for Image Annotation and Tag Refinement
These comments can be a description of the image, or some objects, attributes, scenes in it, which are normally used as the user-provided tags.
SSDH: Semi-supervised Deep Hashing for Large Scale Image Retrieval
(2) A semi-supervised deep hashing network is designed to extensively exploit both labeled and unlabeled data, in which we propose an online graph construction method to benefit from the evolving deep features during training to better capture semantic neighbors.
Towards Automatic Construction of Diverse, High-quality Image Dataset
To eliminate manual annotation, in this work, we propose a novel image dataset construction framework by employing multiple textual queries.
Deep Learning at 15PF: Supervised and Semi-Supervised Classification for Scientific Data
This paper presents the first, 15-PetaFLOP Deep Learning system for solving scientific pattern classification problems on contemporary HPC architectures.
Place recognition: An Overview of Vision Perspective
Place recognition is one of the most fundamental topics in computer vision and robotics communities, where the task is to accurately and efficiently recognize the location of a given query image.
A New Probabilistic Algorithm for Approximate Model Counting
Constrained counting is important in domains ranging from artificial intelligence to software analysis.
Query-adaptive Image Retrieval by Deep Weighted Hashing
On the other hand, different hash bits actually contribute to the image retrieval differently, and treating them equally greatly affects the retrieval accuracy of image.
Exploiting Web Images for Dataset Construction: A Domain Robust Approach
To reduce the cost of manual labelling, there has been increased research interest in automatically constructing image datasets by exploiting web images.
Refining Image Categorization by Exploiting Web Images and General Corpus
To tackle these problems, in this work, we exploit general corpus information to automatically select and subsequently classify web images into semantic rich (sub-)categories.
Multi-Label Image Classification with Regional Latent Semantic Dependencies
Recent state-of-the-art approaches to multi-label image classification exploit the label dependencies in an image, at global level, largely improving the labeling capacity.
A coarse-to-fine algorithm for registration in 3D street-view cross-source point clouds
In this paper, different from previous ICP-based methods, and from a statistic view, we propose a effective coarse-to-fine algorithm to detect and register a small scale SFM point cloud in a large scale Lidar point cloud.
A Systematic Approach for Cross-source Point Cloud Registration by Preserving Macro and Micro Structures
We propose a systematic approach for registering cross-source point clouds.
Parallel SGD: When does averaging help?
Consider a number of workers running SGD independently on the same pool of data and averaging the models every once in a while -- a common but not well understood practice.
A Tool for Computing and Estimating the Volume of the Solution Space of SMT(LA)
There are already quite a few tools for solving the Satisfiability Modulo Theories (SMT) problems.
Abrupt Motion Tracking via Nearest Neighbor Field Driven Stochastic Sampling
Stochastic sampling based trackers have shown good performance for abrupt motion tracking so that they have gained popularity in recent years.
Image Restoration Using Joint Statistical Modeling in Space-Transform Domain
This paper presents a novel strategy for high-fidelity image restoration by characterizing both local smoothness and nonlocal self-similarity of natural images in a unified statistical manner.
Image Compressive Sensing Recovery Using Adaptively Learned Sparsifying Basis via L0 Minimization
From many fewer acquired measurements than suggested by the Nyquist sampling theory, compressive sensing (CS) theory demonstrates that, a signal can be reconstructed with high probability when it exhibits sparsity in some domain.
Structural Group Sparse Representation for Image Compressive Sensing Recovery
Compressive Sensing (CS) theory shows that a signal can be decoded from many fewer measurements than suggested by the Nyquist sampling theory, when the signal is sparse in some domain.
Spatially Directional Predictive Coding for Block-based Compressive Sensing of Natural Images
At the encoder, for each block of compressive sensing (CS) measurements, the optimal pre-diction is selected from a set of prediction candidates that are generated by four designed directional predictive modes.
Characterizing A Database of Sequential Behaviors with Latent Dirichlet Hidden Markov Models
These sequence-level latent parameters for each sequence are modeled as latent Dirichlet random variables and parameterized by a set of deterministic database-level hyper-parameters.
Scene Text Recognition from Two-Dimensional Perspective
Inspired by speech recognition, recent state-of-the-art algorithms mostly consider scene text recognition as a sequence prediction problem.
Ranked #32 on
Scene Text Recognition
on SVT
Performance assessment of the deep learning technologies in grading glaucoma severity
Among these CNNs, the DenseNet had the highest classification accuracy (i. e., 75. 50%) based on pre-trained weights when using global ROIs, as compared to 65. 50% when using local ROIs.
Face Detection with Effective Feature Extraction
There is an abundant literature on face detection due to its important role in many vision applications.
Fast Gated Neural Domain Adaptation: Language Model as a Case Study
We show that the neural LM perplexity can be reduced by 7. 395 and 12. 011 using the proposed domain adaptation mechanism on the Penn Treebank and News data, respectively.
Topic-Informed Neural Machine Translation
In recent years, neural machine translation (NMT) has demonstrated state-of-the-art machine translation (MT) performance.
Message Passing Inference for Large Scale Graphical Models with High Order Potentials
To keep up with the Big Data challenge, parallelized algorithms based on dual decomposition have been proposed to perform inference in Markov random fields.
Multiple Instance Learning on Structured Data
Ignoring this structure information limits the performance of existing MIL algorithms.
Fine-Grained Video Captioning for Sports Narrative
First, to facilitate this novel research of fine-grained video caption, we collected a novel dataset called Fine-grained Sports Narrative dataset (FSN) that contains 2K sports videos with ground-truth narratives from YouTube. com.
Goal-Oriented Visual Question Generation via Intermediate Rewards
Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge.
Assessment of central serous chorioretinopathy (CSC) depicted on color fundus photographs using deep Learning
To investigate whether and to what extent central serous chorioretinopathy (CSC) depicted on color fundus photographs can be assessed using deep learning technology.
Image Denoising via Adaptive Soft-Thresholding Based on Non-Local Samples
To estimate the expectation and variance parameters for the transform bands of a particular patch, we exploit the non-local correlation of image and collect a set of similar patches as data samples to form the distribution.
Higher-Order Inference for Multi-Class Log-Supermodular Models
Higher-order models have been shown to be very useful for a plethora of computer vision tasks.
Unsupervised Part Mining for Fine-grained Image Classification
To tackle this issue, we propose a fully unsupervised part mining (UPM) approach to localize the discriminative parts without even image-level annotations, which largely improves the fine-grained classification performance.
Learning Extreme Hummingbird Maneuvers on Flapping Wing Robots
Inspired by the hummingbirds' near-maximal performance during such extreme maneuvers, we developed a flight control strategy and experimentally demonstrated that such maneuverability can be achieved by an at-scale 12-gram hummingbird robot equipped with just two actuators.
Fast Registration for cross-source point clouds by using weak regional affinity and pixel-wise refinement
Accurate and fast registration of cross-source 3D point clouds from different sensors is an emerged research problem in computer vision.
Towards Locally Consistent Object Counting with Constrained Multi-stage Convolutional Neural Networks
Towards this problem, in this paper we propose a constrained multi-stage Convolutional Neural Networks (CNNs) to jointly pursue locally consistent density map from two aspects.
Single Pixel Reconstruction for One-stage Instance Segmentation
In this paper, we propose a one-stage framework, SPRNet, which performs efficient instance segmentation by introducing a single pixel reconstruction (SPR) branch to off-the-shelf one-stage detectors.
Local Deep-Feature Alignment for Unsupervised Dimension Reduction
Next, we exploit an affine transformation to align the local deep features of each neighbourhood with the global features.
Low-Memory Neural Network Training: A Technical Report
In this paper we study a fundamental question: How much memory is actually needed to train a neural network?
Inferring the Importance of Product Appearance: A Step Towards the Screenless Revolution
In this paper, we aim to infer the significance of every item's appearance in consumer decision making and identify the group of items that are suitable for screenless shopping.
Structured Discriminative Tensor Dictionary Learning for Unsupervised Domain Adaptation
However, the number of labeled source samples are always limited due to expensive annotation cost in practice, making sub-optimal performance been observed.
Glioma Grade Prediction Using Wavelet Scattering-Based Radiomics
Glioma grading before surgery is very critical for the prognosis prediction and treatment plan making.
Extracting Visual Knowledge from the Internet: Making Sense of Image Data
Recent successes in visual recognition can be primarily attributed to feature representation, learning algorithms, and the ever-increasing size of labeled training data.
Sample Adaptive Multiple Kernel Learning for Failure Prediction of Railway Points
In this paper, we formulate our prediction task as a multiple kernel learning problem with missing kernels.
Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification
A novel low-rank pairwise bilinear pooling operation is proposed to capture the nuanced differences between the support and query images for learning an effective distance metric.
Exploiting Channel Similarity for Accelerating Deep Convolutional Neural Networks
To address the limitations of existing magnitude-based pruning algorithms in cases where model weights or activations are of large and similar magnitude, we propose a novel perspective to discover parameter redundancy among channels and accelerate deep CNNs via channel pruning.
C-RPNs: Promoting Object Detection in real world via a Cascade Structure of Region Proposal Networks
Although two-stage detectors like Faster R-CNN achieved big successes in object detection due to the strategy of extracting region proposals by region proposal network, they show their poor adaption in real-world object detection as a result of without considering mining hard samples during extracting region proposals.
PipeMare: Asynchronous Pipeline Parallel DNN Training
Pipeline parallelism (PP) when training neural networks enables larger models to be partitioned spatially, leading to both lower network communication and overall higher hardware utilization.
Variational Few-Shot Learning
We propose a variational Bayesian framework for enhancing few-shot learning performance.
Worst Cases Policy Gradients
Recent advances in deep reinforcement learning have demonstrated the capability of learning complex control policies from many types of environments.
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).
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.
Relational Mimic for Visual Adversarial Imitation Learning
In this work, we introduce a new method for imitation learning from video demonstrations.
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
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.
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.
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.
DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks
On one hand, we can reduce the computation cost remarkably while maintaining the performance.
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.
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.
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).
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.
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.
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
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.
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.
Face Anti-Spoofing Via Disentangled Representation Learning
Face anti-spoofing is crucial to security of face recognition systems.
Computational prediction of RNA tertiary structures using machine learning methods
RNAs play crucial and versatile roles in biological processes.
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.
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.
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.
Uncertainty Weighted Offline Reinforcement Learning
Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration.
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.
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.
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.
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.
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
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
Rigid and Articulated Point Registration with Expectation Conditional Maximization
This paper addresses the issue of matching rigid and articulated shapes through probabilistic point registration.
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.
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.
Counting the Number of Solutions to Constraints
Compared with constraint satisfaction problems, counting problems have received less attention.
Aurora Guard: Reliable Face Anti-Spoofing via Mobile Lighting System
Face authentication on mobile end has been widely applied in various scenarios.
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.
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
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.
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.
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.
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.
Super-Resolving Compressed Video in Coding Chain
Scaling and lossy coding are widely used in video transmission and storage.
Max-min Fairness of K-user Cooperative Rate-Splitting in MISO Broadcast Channel with User Relaying
Cooperative Rate-Splitting (CRS) strategy, relying on linearly precoded rate-splitting at the transmitter and opportunistic transmission of the common message by the relaying user, has recently been shown to outperform typical Non-cooperative Rate-Splitting (NRS), Cooperative Non-Orthogonal Multiple Access (C-NOMA) and Space Division Multiple Access (SDMA) in a two-user Multiple Input Single Output (MISO) Broadcast Channel (BC) with user relaying.
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.
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.
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.
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.
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.
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.
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.
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.
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).
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.
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.
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.
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).
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.
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.
DyNet: Dynamic Convolution for Accelerating Convolution Neural Networks
To verify the scalability, we also apply DyNet on segmentation task, the results show that DyNet can reduces 69. 3% FLOPs while maintaining the Mean IoU on segmentation task.
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.
Quantifying Robustness to Adversarial Word Substitutions
Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations.
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.
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.
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).
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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).
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.
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.
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.
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.
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.
Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration
Deep point cloud registration methods face challenges to partial overlaps and rely on labeled data.
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.
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.
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.
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.
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.
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.
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)
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization
This paper presents GIR, a 3D Gaussian Inverse Rendering method for relightable scene factorization.
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.
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.
Language-Assisted 3D Scene Understanding
The scale and quality of point cloud datasets constrain the advancement of point cloud learning.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
F$^3$low: Frame-to-Frame Coarse-grained Molecular Dynamics with SE(3) Guided Flow Matching
Molecular dynamics (MD) is a crucial technique for simulating biological systems, enabling the exploration of their dynamic nature and fostering an understanding of their functions and properties.
Structured Control Nets for Deep Reinforcement Learning
The proposed Structured Control Net (SCN) splits the generic MLP into two separate sub-modules: a nonlinear control module and a linear control module.
Parameter Efficient Deep Neural Networks with Bilinear Projections
Recent research on deep neural networks (DNNs) has primarily focused on improving the model accuracy.
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.
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.
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.
Deep Bi-Dense Networks for Image Super-Resolution
In this way, feature information propagates from a single dense block to all subsequent blocks, instead of to a single successor.
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.
Generative Structural Design Integrating BIM and Diffusion Model
This study proposes a comprehensive solution.
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?
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.
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?"
Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning
Unlike traditional deep bilinear networks for fine-grained classification, which adopt the self-bilinear pooling to capture the subtle features of images, the proposed model uses a novel pairwise bilinear pooling to compare the nuanced differences between base images and query images for learning a deep distance metric.
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.
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.
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.
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.
