Search Results for author:
Found 184 papers, 80 papers with code
Asymmetric Mutual Learning for Multi-source Unsupervised Sentiment Adaptation with Dynamic Feature Network
Recently, fine-tuning the pre-trained language model (PrLM) on labeled sentiment datasets demonstrates impressive performance.
Treasures Outside Contexts: Improving Event Detection via Global Statistics
Event detection (ED) aims at identifying event instances of specified types in given texts, which has been formalized as a sequence labeling task.
Sparse Covariance Modeling in High Dimensions with Gaussian Processes
This paper studies statistical relationships among components of high-dimensional observations varying across non-random covariates.
Reflection Separation via Multi-bounce Polarization State Tracing
Through a combination of a new polarization-guided image formation model and a novel supervised learning framework for the interpretation of a ray-tracing polarized image formation model, a general method is obtained to tackle general image reflection removal problems.
KnowLogic: A Benchmark for Commonsense Reasoning via Knowledge-Driven Data Synthesis
This approach, along with our benchmark, provides a valuable tool for assessing and enhancing LLMs' commonsense reasoning capabilities and can be applied to a wide range of knowledge domains.
From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models
Aligning large vision-language models (LVLMs) with human preferences is challenging due to the scarcity of fine-grained, high-quality, and multimodal preference data without human annotations.
Towards An Efficient LLM Training Paradigm for CTR Prediction
Despite such promising results, the computational inefficiency inherent in the current training paradigm makes it particularly challenging to train LLMs for ranking-based recommendation tasks on large datasets.
Model Adaptation: Unsupervised Domain Adaptation without Source Data
We aim to explore how to rely only on unlabeled target data to improve performance of an existing source prediction model on the target domain, since labeled source data may not be available in some real-world scenarios due to data privacy issues.
AeroReformer: Aerial Referring Transformer for UAV-based Referring Image Segmentation
While referring image segmentation (RIS) has been extensively studied in natural images, little attention has been given to aerial imagery, particularly from unmanned aerial vehicles (UAVs).
Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming
Large Language Models (LLMs) have gained increasing attention for their remarkable capacity, alongside concerns about safety arising from their potential to produce harmful content.
How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation
Recently, LLMs have garnered increasing attention across academic disciplines for their potential as human digital twins, virtual proxies designed to replicate individuals and autonomously perform tasks such as decision-making, problem-solving, and reasoning on their behalf.
SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
To address this gap, we present SuperGPQA, a comprehensive benchmark that evaluates graduate-level knowledge and reasoning capabilities across 285 disciplines.
Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models
Sentence embedding is essential for many NLP tasks, with contrastive learning methods achieving strong performance using annotated datasets like NLI.
FedP$^2$EFT: Federated Learning to Personalize Parameter Efficient Fine-Tuning for Multilingual LLMs
Federated learning (FL) has enabled the training of multilingual large language models (LLMs) on diverse and decentralized multilingual data, especially on low-resource languages.
A Unified Knowledge-Distillation and Semi-Supervised Learning Framework to Improve Industrial Ads Delivery Systems
Industrial ads ranking systems conventionally rely on labeled impression data, which leads to challenges such as overfitting, slower incremental gain from model scaling, and biases due to discrepancies between training and serving data.
Personalized Interpolation: An Efficient Method to Tame Flexible Optimization Window Estimation
In the realm of online advertising, optimizing conversions is crucial for delivering relevant products to users and enhancing business outcomes.
DeFusion: An Effective Decoupling Fusion Network for Multi-Modal Pregnancy Prediction
Temporal embryo images and parental fertility table indicators are both valuable for pregnancy prediction in \textbf{in vitro fertilization embryo transfer} (IVF-ET).
Plug-and-Play Training Framework for Preference Optimization
Recently, preference optimization methods such as DPO have significantly enhanced large language models (LLMs) in wide tasks including dialogue and question-answering.
TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System
In this paper, we propose TrendSim, an LLM-based multi-agent system to simulate trending topics in social media under poisoning attacks.
SegACIL: Solving the Stability-Plasticity Dilemma in Class-Incremental Semantic Segmentation
Extensive experiments on the Pascal VOC2012 dataset show that SegACIL achieves superior performance in the sequential, disjoint, and overlap settings, offering a robust solution to the challenges of class-incremental semantic segmentation.
A Flexible Plug-and-Play Module for Generating Variable-Length
The NHL framework introduces a novel mechanism to simultaneously generate hash codes of varying lengths in a nested manner.
Deep Learning-Enhanced Preconditioning for Efficient Conjugate Gradient Solvers in Large-Scale PDE Systems
Preconditioning techniques are crucial for enhancing the efficiency of solving large-scale linear equation systems that arise from partial differential equation (PDE) discretization.
CardOOD: Robust Query-driven Cardinality Estimation under Out-of-Distribution
As these learning techniques are originally evaluated in computervision tasks, we also propose a new learning algorithm that exploits the property of cardinality estimation.
Post-hoc Probabilistic Vision-Language Models
Vision-language models (VLMs), such as CLIP and SigLIP, have found remarkable success in classification, retrieval, and generative tasks.
PoTable: Programming Standardly on Table-based Reasoning Like a Human Analyst
Table-based reasoning has garnered substantial research interest, particularly in its integration with Large Language Model (LLM) which has revolutionized the general reasoning paradigm.
Streamlining Prediction in Bayesian Deep Learning
The rising interest in Bayesian deep learning (BDL) has led to a plethora of methods for estimating the posterior distribution.
NeRF Inpainting with Geometric Diffusion Prior and Balanced Score Distillation
The limitations manifest in two critical aspects: the inadequate capture of geometric information by pretrained diffusion models and the suboptimal guidance provided by existing Score Distillation Sampling (SDS) methods.
StableV2V: Stablizing Shape Consistency in Video-to-Video Editing
Recent advancements of generative AI have significantly promoted content creation and editing, where prevailing studies further extend this exciting progress to video editing.
APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and Comments
Datasets play a pivotal role in training visual models, facilitating the development of abstract understandings of visual features through diverse image samples and multidimensional attributes.
A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness
Large language models (LLMs) have demonstrated emergent abilities in text generation, question answering, and reasoning, facilitating various tasks and domains.
CLAP. I. Resolving miscalibration for deep learning-based galaxy photometric redshift estimation
It leverages supervised contrastive learning (SCL) and k-nearest neighbours (KNN) to construct and calibrate raw probability density estimates, and implements a refitting procedure to resume end-to-end discriminative models ready to produce final estimates for large-scale imaging data.
GeoCode-GPT: A Large Language Model for Geospatial Code Generation Tasks
The increasing demand for spatiotemporal data and modeling tasks in geosciences has made geospatial code generation technology a critical factor in enhancing productivity.
Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond
Large language models (LLMs) have not only revolutionized the field of natural language processing (NLP) but also have the potential to bring a paradigm shift in many other fields due to their remarkable abilities of language understanding, as well as impressive generalization capabilities and reasoning skills.
CursorCore: Assist Programming through Aligning Anything
In this work, we propose a new conversational framework that comprehensively integrates these information sources, collect data to train our models and evaluate their performance.
Learning Recommender Systems with Soft Target: A Decoupled Perspective
Learning recommender systems with multi-class optimization objective is a prevalent setting in recommendation.
Explainable Diagnosis Prediction through Neuro-Symbolic Integration
Diagnosis prediction is a critical task in healthcare, where timely and accurate identification of medical conditions can significantly impact patient outcomes.
MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants
LLM-based agents have been widely applied as personal assistants, capable of memorizing information from user messages and responding to personal queries.
Hyperspectral Image Classification Based on Faster Residual Multi-branch Spiking Neural Network
In response to the above problems, this paper builds a spiking neural network (SNN-SWMR) based on the leaky integrate-and-fire (LIF) neuron model for HSI classification tasks.
RePair: Automated Program Repair with Process-based Feedback
The gap between the trepidation of program reliability and the expense of repairs underscores the indispensability of Automated Program Repair (APR).
FSSC: Federated Learning of Transformer Neural Networks for Semantic Image Communication
In this paper, we address the problem of image semantic communication in a multi-user deployment scenario and propose a federated learning (FL) strategy for a Swin Transformer-based semantic communication system (FSSC).
Semantic Successive Refinement: A Generative AI-aided Semantic Communication Framework
To address this issue, we introduce a novel Generative AI Semantic Communication (GSC) system for single-user scenarios.
Enhancing CTR Prediction through Sequential Recommendation Pre-training: Introducing the SRP4CTR Framework
However, these approaches tend to ignore the additional inference costs to the downstream tasks, and they do not consider how to transfer the effective information from the pre-trained models for specific estimated items in CTR prediction.
Training-Free Large Model Priors for Multiple-in-One Image Restoration
To address this issue, we propose Large Model Driven Image Restoration framework (LMDIR), a novel multiple-in-one image restoration paradigm that leverages the generic priors from large multi-modal language models (MMLMs) and the pretrained diffusion models.
Decomposition Betters Tracking Everything Everywhere
DecoMotion explicitly decomposes video content into static scenes and dynamic objects, either of which uses a quasi-3D canonical volume to represent.
Solving the inverse problem of microscopy deconvolution with a residual Beylkin-Coifman-Rokhlin neural network
We validated the m-rBCR model on four microscopy datasets - two simulated microscopy datasets from ImageNet and BioSR, real dSTORM microscopy images, and real widefield microscopy images.
Large Language Models Struggle in Token-Level Clinical Named Entity Recognition
However, there is a significant research gap when it comes to employing token-level NER for clinical texts, especially with the use of local open-source LLMs.
Automated Clinical Data Extraction with Knowledge Conditioned LLMs
To address this, we propose a novel framework that aligns generated internal knowledge with external knowledge through in-context learning (ICL).
Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference
The auto-regressive decoding of Large Language Models (LLMs) results in significant overheads in their hardware performance.
Aligning LLMs through Multi-perspective User Preference Ranking-based Feedback for Programming Question Answering
To address these issues, we propose a novel framework called Aligning LLMs through Multi-perspective User Preference Ranking-based Feedback for Programming Question Answering (ALMupQA) to create user-focused responses.
Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization
Recent advances in knowledge graph embedding (KGE) rely on Euclidean/hyperbolic orthogonal relation transformations to model intrinsic logical patterns and topological structures.
The Third Monocular Depth Estimation Challenge
This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC).
A Survey on the Memory Mechanism of Large Language Model based Agents
Compared with original LLMs, LLM-based agents are featured in their self-evolving capability, which is the basis for solving real-world problems that need long-term and complex agent-environment interactions.
Improving Chinese Character Representation with Formation Tree
This model utilizes formation trees to represent characters and incorporates a dedicated tree encoder, significantly improving performance in both seen and unseen character recognition tasks.
GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo
More specifically, we correspond and propagate adjacent costs to the reference pixel by leveraging the local geometric smoothness in conjunction with surface normals.
Ranked #2 on
3D Reconstruction
on DTU
Flatness Improves Backbone Generalisation in Few-shot Classification
Deployment of deep neural networks in real-world settings typically requires adaptation to new tasks with few examples.
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning
We propose KYN, a novel method for single-view scene reconstruction that reasons about semantic and spatial context to predict each point's density.
Unsupervised Tumor-Aware Distillation for Multi-Modal Brain Image Translation
Existing methods suffer from the problem of brain tumor deformation during translation, as they fail to focus on the tumor areas when translating the whole images.
Graph Image Prior for Unsupervised Dynamic Cardiac Cine MRI Reconstruction
A graph convolutional network is utilized for feature fusion and dynamic image generation.
An Image-based Typology for Visualization
We present and discuss the results of a qualitative analysis of visualization images to derive an image-based typology of visualizations.
TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision
On the other hand, previous weakly-supervised hierarchical text classification methods only utilize the raw taxonomy skeleton and ignore the rich information hidden in the text corpus that can serve as additional class-indicative features.
Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations
Large-scale recommendation systems are characterized by their reliance on high cardinality, heterogeneous features and the need to handle tens of billions of user actions on a daily basis.
Ranked #1 on
Recommendation Systems
on MovieLens 20M
(HR@10 (full corpus) metric)
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors
The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs' responses in an aligned, customizable and explainable manner.
Pan-Mamba: Effective pan-sharpening with State Space Model
To the best of our knowledge, this work is the first attempt in exploring the potential of the Mamba model and establishes a new frontier in the pan-sharpening techniques.
Unveiling the Depths: A Multi-Modal Fusion Framework for Challenging Scenarios
Monocular depth estimation from RGB images plays a pivotal role in 3D vision.
Similarity-based Neighbor Selection for Graph LLMs
Our research further underscores the significance of graph structure integration in LLM applications and identifies key factors for their success in node classification.
Boosting Multi-view Stereo with Late Cost Aggregation
To address this challenge, we present a late aggregation approach that allows for aggregating pairwise costs throughout the network feed-forward process, achieving accurate estimations with only minor changes of the plain CasMVSNet.
Minimally Supervised Learning using Topological Projections in Self-Organizing Maps
In this work, we introduce a semi-supervised learning approach based on topological projections in self-organizing maps (SOMs), which significantly reduces the required number of labeled data points to perform parameter prediction, effectively exploiting information contained in large unlabeled datasets.
Enhancing RAW-to-sRGB with Decoupled Style Structure in Fourier Domain
However, current methods often ignore the difference between cell phone RAW images and DSLR camera RGB images, a difference that goes beyond the color matrix and extends to spatial structure due to resolution variations.
Frequency-Adaptive Pan-Sharpening with Mixture of Experts
Pan-sharpening involves reconstructing missing high-frequency information in multi-spectral images with low spatial resolution, using a higher-resolution panchromatic image as guidance.
Text-conditional Attribute Alignment across Latent Spaces for 3D Controllable Face Image Synthesis
To address these issues we propose a Text-conditional Attribute aLignment approach for 3D controllable face image synthesis and our model is referred to as TcALign.
Two-Stage Adaptive Network for Semi-Supervised Cross-Domain Crater Detection under Varying Scenario Distributions
Experimental results on benchmark datasets demonstrate that the proposed network can enhance domain adaptation ability for crater detection under varying scenario distributions.
Power System Capacity Planning Considering Seasonal Hydrogen Storage by Salt Caverns
To minimize the overall operating cost, a comprehensive power system capacity planning model is proposed with the consideration of hydrogen storage in salt caverns, which is implemented by adopting an improved fast unit commitment method.
A Systematic Review for Transformer-based Long-term Series Forecasting
Various variants have enabled transformer architecture to effectively handle long-term time series forecasting (LTSF) tasks.
The Robust Semantic Segmentation UNCV2023 Challenge Results
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023.
Are Human-generated Demonstrations Necessary for In-context Learning?
In this paper, we raise the fundamental question that whether human-generated demonstrations are necessary for ICL.
Reformulating Sequential Recommendation: Learning Dynamic User Interest with Content-enriched Language Modeling
Recommender systems are indispensable in the realm of online applications, and sequential recommendation has enjoyed considerable prevalence due to its capacity to encapsulate the dynamic shifts in user interests.
Beyond Static Datasets: A Deep Interaction Approach to LLM Evaluation
Existing LLM evaluation methods are mainly supervised signal-based which depends on static datasets and cannot evaluate the ability of LLMs in dynamic real-world scenarios where deep interaction widely exists.
Learning Fine-Grained Features for Pixel-wise Video Correspondences
We address the problem of learning features for establishing pixel-wise correspondences.
TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge
On-device training is essential for user personalisation and privacy.
Improving Hyperparameter Learning under Approximate Inference in Gaussian Process Models
Approximate inference in Gaussian process (GP) models with non-conjugate likelihoods gets entangled with the learning of the model hyperparameters.
Microscopy image reconstruction with physics-informed denoising diffusion probabilistic model
Yet, deep learning models are prone to introduce artefacts and hallucinations into the reconstruction.
Research on Multilingual News Clustering Based on Cross-Language Word Embeddings
(2) We use the LDA topic model to represent news as a combina-tion of cross-lingual vectors for headlines and topic probability distributions for con-tent, introducing concepts such as topic similarity to address the cross-lingual issue in news content representation.
The News Delivery Channel Recommendation Based on Granular Neural Network
As is known, traditional news recommendation systems mostly employ techniques based on collaborative filtering and deep learning, but the performance of these algorithms is constrained by the sparsity of the data and the scalability of the approaches.
To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion
Embedding models have shown great power in knowledge graph completion (KGC) task.
LaCon: Late-Constraint Diffusion for Steerable Guided Image Synthesis
To offer more controllability for the generation process, existing studies, termed as early-constraint methods in this paper, leverage extra conditions and incorporate them into pre-trained diffusion models.
Ranked #1 on
Conditional Text-to-Image Synthesis
on COCO 2017 val
Conditional Image Generation
Conditional Text-to-Image Synthesis
Towards Generalizable Medical Image Segmentation with Pixel-wise Uncertainty Estimation
In contrast, the IID hypothesis is not universally guaranteed in numerous real-world applications, especially in medical image analysis.
Black-box Source-free Domain Adaptation via Two-stage Knowledge Distillation
In Stage \uppercase\expandafter{\romannumeral1}, we train the target model from scratch with soft pseudo-labels generated by the source model in a knowledge distillation manner.
Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenes
To let the geometric perception learned from multi-view cues in static areas propagate to the monocular representation in dynamic areas and let monocular cues enhance the representation of multi-view cost volume, we propose a cross-cue fusion (CCF) module, which includes the cross-cue attention (CCA) to encode the spatially non-local relative intra-relations from each source to enhance the representation of the other.
Feature Alignment and Uniformity for Test Time Adaptation
Test time adaptation (TTA) aims to adapt deep neural networks when receiving out of distribution test domain samples.
LSwinSR: UAV Imagery Super-Resolution based on Linear Swin Transformer
Super-resolution, which aims to reconstruct high-resolution images from low-resolution images, has drawn considerable attention and has been intensively studied in computer vision and remote sensing communities.
Prototype Knowledge Distillation for Medical Segmentation with Missing Modality
Specifically, our ProtoKD can not only distillate the pixel-wise knowledge of multi-modality data to single-modality data but also transfer intra-class and inter-class feature variations, such that the student model could learn more robust feature representation from the teacher model and inference with only one single modality data.
Bootstrap The Original Latent: Learning a Private Model from a Black-box Model
In this paper, considering the balance of data/model privacy of model owners and user needs, we propose a new setting called Back-Propagated Black-Box Adaptation (BPBA) for users to better train their private models via the guidance of the back-propagated results of a Black-box foundation/source model.
Producing Usable Taxonomies Cheaply and Rapidly at Pinterest Using Discovered Dynamic $μ$-Topics
Creating a taxonomy of interests is expensive and human-effort intensive: not only do we need to identify nodes and interconnect them, in order to use the taxonomy, we must also connect the nodes to relevant entities such as users, pins, and queries.
Pyramid Dual Domain Injection Network for Pan-sharpening
To this end, we first revisit the degradation process of pan-sharpening in Fourier space, and then devise a Pyramid Dual Domain Injection Pan-sharpening Network upon the above observation by fully exploring and exploiting the distinguished information in both the spatial and frequency domains.
Heterogeneous Diversity Driven Active Learning for Multi-Object Tracking
HD-AMOT defines the diversified informative representation by encoding the geometric and semantic information, and formulates the frame inference strategy as a Markov decision process to learn an optimal sampling policy based on the designed informative representation.
A Survey on In-context Learning
With the increasing capabilities of large language models (LLMs), in-context learning (ICL) has emerged as a new paradigm for natural language processing (NLP), where LLMs make predictions based on contexts augmented with a few examples.
A Large-scale Friend Suggestion Architecture
There has been little work on designing friend suggestion when facing these difficulties, and for the first time we aim to tackle this in large scale online games.
Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation
Recent image degradation estimation methods have enabled single-image super-resolution (SR) approaches to better upsample real-world images.
Expanding Knowledge Graphs with Humans in the Loop
Concretely, given a knowledge graph, our method predicts the "parents" of new concepts to be added to this graph for further verification by human experts.
NRTR: Neuron Reconstruction with Transformer from 3D Optical Microscopy Images
Existing deep learning neuron reconstruction methods, although demonstrating exemplary performance, greatly demand complex rule-based components.
Predicting Biomedical Interactions with Probabilistic Model Selection for Graph Neural Networks
Experiments on four interaction datasets show that our proposed method achieves accurate and calibrated predictions.
Towards Improved Learning in Gaussian Processes: The Best of Two Worlds
Gaussian process training decomposes into inference of the (approximate) posterior and learning of the hyperparameters.
Learning on Large-scale Text-attributed Graphs via Variational Inference
In this paper, we propose an efficient and effective solution to learning on large text-attributed graphs by fusing graph structure and language learning with a variational Expectation-Maximization (EM) framework, called GLEM.
Ranked #1 on
Node Property Prediction
on ogbn-papers100M
The Future of Consumer Edge-AI Computing
In the last decade, Deep Learning has rapidly infiltrated the consumer end, mainly thanks to hardware acceleration across devices.
Test-Time Training for Graph Neural Networks
To bridge such gap, in this work we introduce the first test-time training framework for GNNs to enhance the model generalization capacity for the graph classification task.
Accelerated partial separable model using dimension-reduced optimization technique for ultra-fast cardiac MRI
The main objective of this study is to accelerate the PS model, shorten the time required for acquisition and reconstruction, and maintain good image quality simultaneously.
Spatial-then-Temporal Self-Supervised Learning for Video Correspondence
Specifically, we firstly extract spatial features from unlabeled images via contrastive learning, and secondly enhance the features by exploiting the temporal cues in unlabeled videos via reconstructive learning.
Learning Multi-Modal Brain Tumor Segmentation from Privileged Semi-Paired MRI Images with Curriculum Disentanglement Learning
Specifically, in the first step, we propose to conduct reconstruction and segmentation with augmented intra-modality style-consistent images.
SFusion: Self-attention based N-to-One Multimodal Fusion Block
To solve this problem, we propose a self-attention based fusion block called SFusion.
A Sahlqvist-style Correspondence Theorem for Linear-time Temporal Logic
The main result of this paper is to prove the correspondence of LTL Sahlqvist formulas to frame conditions that are definable in first-order language.
A Look at Improving Robustness in Visual-inertial SLAM by Moment Matching
The fusion of camera sensor and inertial data is a leading method for ego-motion tracking in autonomous and smart devices.
Unsupervised Multi-Modal Medical Image Registration via Discriminator-Free Image-to-Image Translation
In this paper, we propose a novel translation-based unsupervised deformable image registration approach to convert the multi-modal registration problem to a mono-modal one.
HASA: Hybrid Architecture Search with Aggregation Strategy for Echinococcosis Classification and Ovary Segmentation in Ultrasound Images
The hybrid framework consists of a pre-trained backbone and several searched cells (i. e., network building blocks), which takes advantage of the strengths of both NAS and the expert knowledge from existing convolutional neural networks.
Semantic-guided Disentangled Representation for Unsupervised Cross-modality Medical Image Segmentation
Disentangled representation is a powerful technique to tackle domain shift problem in medical image analysis in unsupervised domain adaptation setting. However, previous methods only focus on exacting domain-invariant feature and ignore whether exacted feature is meaningful for downstream tasks. We propose a novel framework, called semantic-guided disentangled representation (SGDR), an effective method to exact semantically meaningful feature for segmentation task to improve performance of cross modality medical image segmentation in unsupervised domain adaptation setting.
Slice Imputation: Intermediate Slice Interpolation for Anisotropic 3D Medical Image Segmentation
We introduce a novel frame-interpolation-based method for slice imputation to improve segmentation accuracy for anisotropic 3D medical images, in which the number of slices and their corresponding segmentation labels can be increased between two consecutive slices in anisotropic 3D medical volumes.
Neural Adaptive SCEne Tracing
Neural rendering with implicit neural networks has recently emerged as an attractive proposition for scene reconstruction, achieving excellent quality albeit at high computational cost.
HousE: Knowledge Graph Embedding with Householder Parameterization
The effectiveness of knowledge graph embedding (KGE) largely depends on the ability to model intrinsic relation patterns and mapping properties.
NeAT: Neural Adaptive Tomography
Through a combination of neural features with an adaptive explicit representation, we achieve reconstruction times far superior to existing neural inverse rendering methods.
Ranked #4 on
Low-Dose X-Ray Ct Reconstruction
on X3D
Dilated Continuous Random Field for Semantic Segmentation
Mean field approximation methodology has laid the foundation of modern Continuous Random Field (CRF) based solutions for the refinement of semantic segmentation.
Motion-Focused Contrastive Learning of Video Representations
To this end, we compose a duet of exploiting the motion for data augmentation and feature learning in the regime of contrastive learning.
A New Perspective on the Effects of Spectrum in Graph Neural Networks
Many improvements on GNNs can be deemed as operations on the spectrum of the underlying graph matrix, which motivates us to directly study the characteristics of the spectrum and their effects on GNN performance.
Ranked #8 on
Graph Classification
on ENZYMES
Building extraction with vision transformer
Second, spatial details are not sufficiently preserved during the feature extraction of the Vision Transformer, resulting in the inability for fine-grained building segmentation.
Joint Inference for Neural Network Depth and Dropout Regularization
We propose a unified Bayesian model selection method to jointly infer the most plausible network depth warranted by data, and perform dropout regularization simultaneously.
Shape and Reflectance Reconstruction in Uncontrolled Environments by Differentiable Rendering
Simultaneous reconstruction of geometry and reflectance properties in uncontrolled environments remains a challenging problem.
UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery
In this paper, we propose a Transformer-based decoder and construct a UNet-like Transformer (UNetFormer) for real-time urban scene segmentation.
Ranked #1 on
Scene Segmentation
on UAVid
A Channel Coding Benchmark for Meta-Learning
We use our MetaCC benchmark to study several aspects of meta-learning, including the impact of task distribution breadth and shift, which can be controlled in the coding problem.
Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images
Specifically, the dependency path is conducted based on the ResT, a novel Transformer backbone with memory-efficient multi-head self-attention, while the texture path is built on the stacked convolution operation.
Ranked #9 on
Semantic Segmentation
on UAVid
Searching Collaborative Agents for Multi-plane Localization in 3D Ultrasound
First, our proposed method is general and it can accurately localize multiple SPs in different challenging US datasets.
Learn Fine-grained Adaptive Loss for Multiple Anatomical Landmark Detection in Medical Images
Our proposed framework is general and shows the potential to improve the efficiency of anatomical landmark detection.
TarGAN: Target-Aware Generative Adversarial Networks for Multi-modality Medical Image Translation
In this paper, we propose a novel target-aware generative adversarial network called TarGAN, which is a generic multi-modality medical image translation model capable of (1) learning multi-modality medical image translation without relying on paired data, (2) enhancing quality of target area generation with the help of target area labels.
Multiattention network for semantic segmentation of fine-resolution remote sensing images
A novel attention mechanism of kernel attention with linear complexity is proposed to alleviate the large computational demand in attention.
Ranked #7 on
Semantic Segmentation
on ISPRS Vaihingen
A unified Neural Network Approach to E-CommerceRelevance Learning
We describe a highly-scalable feed-forward neural model to provide relevance score for (query, item) pairs, using only user query and item title as features, and both user click feedback as well as limited human ratings as labels.
A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images
The fully convolutional network (FCN) with an encoder-decoder architecture has been the standard paradigm for semantic segmentation.
Ranked #3 on
Semantic Segmentation
on ISPRS Potsdam
(using extra training data)
From Semantic Retrieval to Pairwise Ranking: Applying Deep Learning in E-commerce Search
We introduce deep learning models to the two most important stages in product search at JD. com, one of the largest e-commerce platforms in the world.
Scale-aware Neural Network for Semantic Segmentation of Multi-resolution Remote Sensing Images
However, MSR images suffer from two critical issues: 1) increased scale variation of geo-objects and 2) loss of detailed information at coarse spatial resolutions.
A2-FPN for Semantic Segmentation of Fine-Resolution Remotely Sensed Images
Based on FPN and AAM, a novel framework named Attention Aggregation Feature Pyramid Network (A2-FPN) is developed for semantic segmentation of fine-resolution remotely sensed images.
Learning Depth via Leveraging Semantics: Self-supervised Monocular Depth Estimation with Both Implicit and Explicit Semantic Guidance
While the mappings between image and pixel-wise depth are well-studied in current methods, the correlation between image, depth and scene semantics, however, is less considered.
Adaptive Processor Frequency Adjustment for Mobile Edge Computing with Intermittent Energy Supply
With astonishing speed, bandwidth, and scale, Mobile Edge Computing (MEC) has played an increasingly important role in the next generation of connectivity and service delivery.
ABCNet: Attentive Bilateral Contextual Network for Efficient Semantic Segmentation of Fine-Resolution Remote Sensing Images
Specifically, the high-caliber performance of the convolutional neural network (CNN) heavily relies on fine-grained spatial details (fine resolution) and sufficient contextual information (large receptive fields), both of which trigger high computational costs.
Ranked #8 on
Semantic Segmentation
on ISPRS Vaihingen
Analytical Characterization and Design Space Exploration for Optimization of CNNs
Moving data through the memory hierarchy is a fundamental bottleneck that can limit the performance of core algorithms of machine learning, such as convolutional neural networks (CNNs).
Non-uniform Motion Deblurring with Blurry Component Divided Guidance
To tackle the above problems, we present a deep two-branch network to deal with blurry images via a component divided module, which divides an image into two components based on the representation of blurry degree.
Generalize Ultrasound Image Segmentation via Instant and Plug & Play Style Transfer
Deep segmentation models that generalize to images with unknown appearance are important for real-world medical image analysis.
IntraTomo: Self-Supervised Learning-Based Tomography via Sinogram Synthesis and Prediction
After getting estimated through the sinogram prediction module, the density field is consistently refined in the second module using local and non-local geometrical priors.
Ranked #6 on
Novel View Synthesis
on X3D
Computed Tomography (CT)
Low-Dose X-Ray Ct Reconstruction
+3
VIS30K: A Collection of Figures and Tables from IEEE Visualization Conference Publications
We present the VIS30K dataset, a collection of 29, 689 images that represents 30 years of figures and tables from each track of the IEEE Visualization conference series (Vis, SciVis, InfoVis, VAST).
Multi-Head Linear Attention Generative Adversarial Network for Thin Cloud Removal
In remote sensing images, the existence of the thin cloud is an inevitable and ubiquitous phenomenon that crucially reduces the quality of imageries and limits the scenarios of application.
Semantic-Guided Representation Enhancement for Self-supervised Monocular Trained Depth Estimation
Based on this framework, we enhance the local feature representation by sampling and feeding the point-based features that locate on the semantic edges to an individual Semantic-guided Edge Enhancement module (SEEM), which is specifically designed for promoting depth estimation on the challenging semantic borders.
Dynamic Fusion of Eye Movement Data and Verbal Narrations in Knowledge-rich Domains
We propose to jointly analyze experts' eye movements and verbal narrations to discover important and interpretable knowledge patterns to better understand their decision-making processes.
Multi-stage Attention ResU-Net for Semantic Segmentation of Fine-Resolution Remote Sensing Images
The attention mechanism can refine the extracted feature maps and boost the classification performance of the deep network, which has become an essential technique in computer vision and natural language processing.
Eliminating the Barriers: Demystifying Wi-Fi Baseband Design and Introducing the PicoScenes Wi-Fi Sensing Platform
Three barriers always hamper the research: unknown baseband design and its influence, inadequate hardware, and the lack of versatile and flexible measurement software.
Hardware Architecture
Interpretable Structured Learning with Sparse Gated Sequence Encoder for Protein-Protein Interaction Prediction
Although various deep learning models in Siamese architecture have been proposed to model PPIs from sequences, these methods are computationally expensive for a large number of PPIs due to the pairwise encoding process.
Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks
Recently, graph neural networks have been proposed to effectively learn representations for biomedical entities and achieved state-of-the-art results in biomedical interaction prediction.
Ranked #1 on
Link Prediction
on Drug-target interactions
Contrastive Rendering for Ultrasound Image Segmentation
However, the lack of sharp boundaries in US images still remains an inherent challenge for segmentation.
Multi-Attention-Network for Semantic Segmentation of Fine Resolution Remote Sensing Images
A novel attention mechanism of kernel attention with linear complexity is proposed to alleviate the large computational demand in attention.
Thick Cloud Removal of Remote Sensing Images Using Temporal Smoothness and Sparsity-Regularized Tensor Optimization
In this paper, a novel thick cloud removal method for remote sensing images based on temporal smoothness and sparsity-regularized tensor optimization (TSSTO) is proposed.
Land Cover Classification from Remote Sensing Images Based on Multi-Scale Fully Convolutional Network
In this paper, a Multi-Scale Fully Convolutional Network (MSFCN) with multi-scale convolutional kernel is proposed to exploit discriminative representations from two-dimensional (2D) satellite images.
Searching Collaborative Agents for Multi-plane Localization in 3D Ultrasound
In this study, we propose a novel Multi-Agent Reinforcement Learning (MARL) framework to localize multiple uterine SPs in 3D US simultaneously.
Research on Fitness Function of Two Evolution Algorithms Used for Neutron Spectrum Unfolding
In this work, we investigated the performance of eight fitness functions attached to the genetic algorithm (GA) and the differential evolution algorithm (DEA) used for unfolding four neutron spectra selected from the IAEA 403 report.
Linear Attention Mechanism: An Efficient Attention for Semantic Segmentation
In this paper, to remedy this deficiency, we propose a Linear Attention Mechanism which is approximate to dot-product attention with much less memory and computational costs.
MACU-Net for Semantic Segmentation of Fine-Resolution Remotely Sensed Images
In this Letter, we incorporate multi-scale features generated by different layers of U-Net and design a multi-scale skip connected and asymmetric-convolution-based U-Net (MACU-Net), for segmentation using fine-resolution remotely sensed images.
LiteDenseNet: A Lightweight Network for Hyperspectral Image Classification
Hyperspectral Image (HSI) classification based on deep learning has been an attractive area in recent years.
G-Net: A Deep Learning Approach to G-computation for Counterfactual Outcome Prediction Under Dynamic Treatment Regimes
Counterfactual prediction is a fundamental task in decision-making.
MODMA dataset: a Multi-modal Open Dataset for Mental-disorder Analysis
The EEG dataset includes not only data collected using traditional 128-electrodes mounted elastic cap, but also a novel wearable 3-electrode EEG collector for pervasive applications.
Robust Data Preprocessing for Machine-Learning-Based Disk Failure Prediction in Cloud Production Environments
To provide proactive fault tolerance for modern cloud data centers, extensive studies have proposed machine learning (ML) approaches to predict imminent disk failures for early remedy and evaluated their approaches directly on public datasets (e. g., Backblaze SMART logs).
Multivariate Sparse Coding of Nonstationary Covariances with Gaussian Processes
This paper studies statistical characteristics of multivariate observations with irregular changes in their covariance structures across input space.
Validation of image-guided cochlear implant programming techniques
In this article, we create a ground truth dataset with conventional CT and micro-CT images of 35 temporal bone specimens to both rigorously characterize the accuracy of these two steps and assess how inaccuracies in these steps affect the overall results.
A Convolutional Neural Network with Mapping Layers for Hyperspectral Image Classification
In this paper, we propose a convolutional neural network with mapping layers (MCNN) for hyperspectral image (HSI) classification.
Adaptive Noise Injection: A Structure-Expanding Regularization for RNN
Due to the adaptive noises can be improved as the training processes, its negative effects can be weakened and even transformed into a positive effect to further improve the expressiveness of the main-branch RNN.
Neural Embedding for Physical Manipulations
In common real-world robotic operations, action and state spaces can be vast and sometimes unknown, and observations are often relatively sparse.
Use of OWL and Semantic Web Technologies at Pinterest
In this paper, we present the engineering of an OWL ontology---the Pinterest Taxonomy---that forms the core of Pinterest's knowledge graph, the Pinterest Taste Graph.
Imitating Targets from all sides: An Unsupervised Transfer Learning method for Person Re-identification
Person re-identification (Re-ID) models usually show a limited performance when they are trained on one dataset and tested on another dataset due to the inter-dataset bias (e. g. completely different identities and backgrounds) and the intra-dataset difference (e. g. camera invariance).
GNE: a deep learning framework for gene network inference by aggregating biological information
However, it is still a challenging task to aggregate heterogeneous biological information such as gene expression and gene interactions to achieve more accurate inference for prediction and discovery of new gene interactions.
Ranked #1 on
Gene Interaction Prediction
on BioGRID(yeast)
(using extra training data)
Deep Distribution Regression
Due to their flexibility and predictive performance, machine-learning based regression methods have become an important tool for predictive modeling and forecasting.
Towards Machine Learning Prediction of Deep Brain Stimulation (DBS) Intra-operative Efficacy Maps
We show an improvement in the classification of intraoperative stimulation coordinates as a positive response in reduction of symptoms with AUC of 0. 670 compared to a baseline registration-based approach, which achieves an AUC of 0. 627 (p < 0. 01).
Driver Behavior Recognition via Interwoven Deep Convolutional Neural Nets with Multi-stream Inputs
Experiments conducted with a dataset that we collect in a mock-up car environment demonstrate that the proposed InterCNN with MobileNet convolutional blocks can classify 9 different behaviors with 73. 97% accuracy, and 5 'aggregated' behaviors with 81. 66% accuracy.
Fast Symbolic 3D Registration Solution
3D registration has always been performed invoking singular value decomposition (SVD) or eigenvalue decomposition (EIG) in real engineering practices.
Participation of an energy hub in electricity and heat distribution markets: An mpec approach
A mathematic program with equilibrium constraints (MPEC) model is proposed to study the strategic behaviors of a profit-driven energy hub in the electricity market and heating market under the background of energy system integration.
Optimal dispatch of zero-carbon-emission micro energy Internet integrated with non-supplementary fired compressed air energy storage system
Optimal operation of the ZCE-MEI is firstly modeled as a mixed integer nonlinear programming (MINLP).
Patch-based Texture Synthesis for Image Inpainting
We form it as an optimization problem that identifies the potential patches for synthesis from an coarse-to-fine manner.
Multiobjective Optimization of Classifiers by Means of 3-D Convex Hull Based Evolutionary Algorithm
The design of the algorithm proposed in this paper is inspired by indicator-based evolutionary algorithms, where first a performance indicator for a solution set is established and then a selection operator is designed that complies with the performance indicator.
Sensing and Recognizing Surface Textures Using a GelSight Sensor
Sensing surface textures by tou ch is a valuable was difficult to build capability for robots.
Image Understanding from Experts' Eyes by Modeling Perceptual Skill of Diagnostic Reasoning Processes
Eliciting and representing experts' remarkable perceptual capability of locating, identifying and categorizing objects in images specific to their domains of expertise will benefit image understanding in terms of transferring human domain knowledge and perceptual expertise into image-based computational procedures.
