Search Results for author:
Found 187 papers, 56 papers with code
Multi-Attribute Controlled Text Generation with Contrastive-Generator and External-Discriminator
To achieve this, we design a contrastive-generator that can effectively generate texts with more attributes.
EgoPrivacy: What Your First-Person Camera Says About You?
While the rapid proliferation of wearable cameras has raised significant concerns about egocentric video privacy, prior work has largely overlooked the unique privacy threats posed to the camera wearer.
The Invariant Zonotopic Set-Membership Filter for State Estimation on Groups
In this paper, considering the problem of state estimation with unknown but bounded noise disturbances, an Invariant Zonotopic Set-Membership Filter (InZSMF) method on groups is innovatively proposed, which extends the invariant filtering theory to the field of non-statistical filtering represented by set-membership filtering.
SDN-Based False Data Detection With Its Mitigation and Machine Learning Robustness for In-Vehicle Networks
In an in-vehicle network, these ECUs communicate with one another using an standard protocol called Controller Area Network (CAN).
UniEval: Unified Holistic Evaluation for Unified Multimodal Understanding and Generation
However, there is a lack of a unified evaluation framework for these models, which would enable an elegant, simplified, and overall evaluation.
Leveraging Segment Anything Model for Source-Free Domain Adaptation via Dual Feature Guided Auto-Prompting
Source-free domain adaptation (SFDA) for segmentation aims at adapting a model trained in the source domain to perform well in the target domain with only the source model and unlabeled target data. Inspired by the recent success of Segment Anything Model (SAM) which exhibits the generality of segmenting images of various modalities and in different domains given human-annotated prompts like bounding boxes or points, we for the first time explore the potentials of Segment Anything Model for SFDA via automatedly finding an accurate bounding box prompt.
Transformer-Based Dual-Optical Attention Fusion Crowd Head Point Counting and Localization Network
In this paper, the dual-optical attention fusion crowd head point counting model (TAPNet) is proposed to address the problem of the difficulty of accurate counting in complex scenes such as crowd dense occlusion and low light in crowd counting tasks under UAV view.
Ranked #1 on
Crowd Counting
on DroneRGBT
TS-Diff: Two-Stage Diffusion Model for Low-Light RAW Image Enhancement
During the aligning stage, CFIs are averaged to create a target-specific CFI$^T$, which is fine-tuned using a small amount of real RAW data to adapt to the noise characteristics of specific cameras.
Inferring Outcome Means of Exponential Family Distributions Estimated by Deep Neural Networks
While deep neural networks (DNNs) are widely used for prediction, inference on DNN-estimated subject-specific means for categorical or exponential family outcomes remains underexplored.
Prototype-Based Continual Learning with Label-free Replay Buffer and Cluster Preservation Loss
These mechanisms ensure the retention of previously learned information as well as adaptation to new classes or domain shifts.
Intelligent Bear Prevention System Based on Computer Vision: An Approach to Reduce Human-Bear Conflicts in the Tibetan Plateau Area, China
Conflicts between humans and bears on the Tibetan Plateau present substantial threats to local communities and hinder wildlife preservation initiatives.
Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations
To address this, we introduce the Cascaded Organized Bi-Represented generAtive retrieval (COBRA) framework, which innovatively integrates sparse semantic IDs and dense vectors through a cascading process.
Split Adaptation for Pre-trained Vision Transformers
SA, inspired by split learning (SL), segments the pre-trained ViT into a frontend and a backend, with only the frontend shared with the client for data representation extraction.
Never too Prim to Swim: An LLM-Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions
The adaptivity and maneuvering capabilities of Autonomous Underwater Vehicles (AUVs) have drawn significant attention in oceanic research, due to the unpredictable disturbances and strong coupling among the AUV's degrees of freedom.
Near-optimal Active Regression of Single-Index Models
The active regression problem of the single-index model is to solve $\min_x \lVert f(Ax)-b\rVert_p$, where $A$ is fully accessible and $b$ can only be accessed via entry queries, with the goal of minimizing the number of queries to the entries of $b$.
Towards Secure Program Partitioning for Smart Contracts with LLM's In-Context Learning
Smart contracts are highly susceptible to manipulation attacks due to the leakage of sensitive information.
DeFiScope: Detecting Various DeFi Price Manipulations with LLM Reasoning
DeFi (Decentralized Finance) is one of the most important applications of today's cryptocurrencies and smart contracts.
HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation
Large foundation models have shown strong open-world generalization to complex problems in vision and language, but similar levels of generalization have yet to be achieved in robotics.
Consensus statement on the credibility assessment of ML predictors
The rapid integration of machine learning (ML) predictors into in silico medicine has revolutionized the estimation of quantities of interest (QIs) that are otherwise challenging to measure directly.
Continual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks
Extensive experiments demonstrate that CauSiam effectively improves the generalization performance of existing SIDD methods in continuously changing domains.
Efficiently Serving Large Multimodal Models Using EPD Disaggregation
Large Multimodal Models (LMMs) extend Large Language Models (LLMs) by handling diverse inputs such as images, audio, and video, but at the cost of adding a multimodal encoding stage that increases both computational and memory overhead.
Toward Fair Graph Neural Networks Via Dual-Teacher Knowledge Distillation
To enhance information transfer, we incorporate graph-level distillation to provide an indirect supplement of graph information during training, as well as a node-specific temperature module to improve the comprehensive transfer of fair knowledge.
Dynamic Attention and Bi-directional Fusion for Safety Helmet Wearing Detection
Ensuring construction site safety requires accurate and real-time detection of workers' safety helmet use, despite challenges posed by cluttered environments, densely populated work areas, and hard-to-detect small or overlapping objects caused by building obstructions.
GRAPE: Generalizing Robot Policy via Preference Alignment
Notably, these constraints are flexible and can be customized to align the model with varying objectives, such as safety, efficiency, or task success.
Neural-Network-Enhanced Metalens Camera for High-Definition, Dynamic Imaging in the Long-Wave Infrared Spectrum
To provide a lightweight and cost-effective solution for the long-wave infrared imaging using a singlet, we develop a camera by integrating a High-Frequency-Enhancing Cycle-GAN neural network into a metalens imaging system.
LEADRE: Multi-Faceted Knowledge Enhanced LLM Empowered Display Advertisement Recommender System
Display advertising provides significant value to advertisers, publishers, and users.
YOSO: You-Only-Sample-Once via Compressed Sensing for Graph Neural Network Training
Graph neural networks (GNNs) have become essential tools for analyzing non-Euclidean data across various domains.
Multi-Objective-Optimization Multi-AUV Assisted Data Collection Framework for IoUT Based on Offline Reinforcement Learning
To address these issues and the constraints of turbulent ocean environments, we propose a multi-AUV assisted data collection framework for IoUT based on multi-agent offline RL.
EFILN: The Electric Field Inversion-Localization Network for High-Precision Underwater Positioning
Accurate underwater target localization is essential for underwater exploration.
OptiGrasp: Optimized Grasp Pose Detection Using RGB Images for Warehouse Picking Robots
In warehouse environments, robots require robust picking capabilities to manage a wide variety of objects.
ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models
To this end, we propose \textbf{\textit{ChemEval}}, which provides a comprehensive assessment of the capabilities of LLMs across a wide range of chemical domain tasks.
SX-Stitch: An Efficient VMS-UNet Based Framework for Intraoperative Scoliosis X-Ray Image Stitching
In scoliosis surgery, the limited field of view of the C-arm X-ray machine restricts the surgeons' holistic analysis of spinal structures . This paper presents an end-to-end efficient and robust intraoperative X-ray image stitching method for scoliosis surgery, named SX-Stitch.
Community-Centric Graph Unlearning
Graph unlearning technology has become increasingly important since the advent of the `right to be forgotten' and the growing concerns about the privacy and security of artificial intelligence.
Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms
Our algorithm can be extended to the $\ell_p$ sparse recovery problem with the same sketching dimension, which seems to be the first such bound for $p > 2$.
Fairness and Bias Mitigation in Computer Vision: A Survey
Computer vision systems have witnessed rapid progress over the past two decades due to multiple advances in the field.
Topology Optimization of Random Memristors for Input-Aware Dynamic SNN
To address these fundamental challenges, we introduce pruning optimization for input-aware dynamic memristive spiking neural network (PRIME).
U-learning for Prediction Inference via Combinatory Multi-Subsampling: With Applications to LASSO and Neural Networks
Epigenetic aging clocks play a pivotal role in estimating an individual's biological age through the examination of DNA methylation patterns at numerous CpG (Cytosine-phosphate-Guanine) sites within their genome.
Self-Supervised Representation Learning for Adversarial Attack Detection
Experimental results show that, compared to various benchmark self-supervised vision learning models and supervised adversarial attack detection methods, the proposed model achieves state-of-the-art performance on the adversarial attack detection task across a wide range of images.
UNICAD: A Unified Approach for Attack Detection, Noise Reduction and Novel Class Identification
As the use of Deep Neural Networks (DNNs) becomes pervasive, their vulnerability to adversarial attacks and limitations in handling unseen classes poses significant challenges.
PUDD: Towards Robust Multi-modal Prototype-based Deepfake Detection
Deepfake techniques generate highly realistic data, making it challenging for humans to discern between actual and artificially generated images.
Federated Adversarial Learning for Robust Autonomous Landing Runway Detection
As the development of deep learning techniques in autonomous landing systems continues to grow, one of the major challenges is trust and security in the face of possible adversarial attacks.
Teleporter Theory: A General and Simple Approach for Modeling Cross-World Counterfactual Causality
Leveraging the development of structural causal model (SCM), researchers can establish graphical models for exploring the causal mechanisms behind machine learning techniques.
Revisiting Spurious Correlation in Domain Generalization
To this end, we explore to build a SCM for representation learning process and further conduct a thorough analysis of the mechanisms underlying spurious correlation.
Interventional Imbalanced Multi-Modal Representation Learning via $β$-Generalization Front-Door Criterion
However, our empirical explorations challenge the fundamental idea behind such behavior, and we further conclude that benchmark approaches suffer from certain defects: insufficient theoretical interpretability and limited exploration capability of discriminative knowledge.
Continuous-Time Digital Twin with Analogue Memristive Neural Ordinary Differential Equation Solver
We experimentally validate our approach by developing a digital twin of the HP memristor, which accurately extrapolates its nonlinear dynamics, achieving a 4. 2-fold projected speedup and a 41. 4-fold projected decrease in energy consumption compared to state-of-the-art digital hardware, while maintaining an acceptable error margin.
One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models
Active learning (AL) for multiple target models aims to reduce labeled data querying while effectively training multiple models concurrently.
Agnostic Active Learning of Single Index Models with Linear Sample Complexity
We provide two main results on agnostic active learning of single index models.
HAGAN: Hybrid Augmented Generative Adversarial Network for Medical Image Synthesis
However, due to the complexity of medical images and similar characteristics of different tissue cells, existing methods face great challenges in meeting their biological consistency.
PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation
With recent advances in large language models (LLMs), this paper explores the potential of leveraging state-of-the-art LLMs, such as GPT-4, to transfer existing human-written properties (e. g., those from Certora auditing reports) and automatically generate customized properties for unknown code.
Federated Graph Learning for EV Charging Demand Forecasting with Personalization Against Cyberattacks
To address these challenges, a federated graph learning approach involving multiple charging stations is proposed to collaboratively train a more generalized deep learning model for demand forecasting while capturing spatial correlations among various stations and enhancing robustness against potential attacks.
Harmonic Machine Learning Models are Robust
We introduce Harmonic Robustness, a powerful and intuitive method to test the robustness of any machine-learning model either during training or in black-box real-time inference monitoring without ground-truth labels.
Cross-Temporal Spectrogram Autoencoder (CTSAE): Unsupervised Dimensionality Reduction for Clustering Gravitational Wave Glitches
In response to this challenge, we introduce the Cross-Temporal Spectrogram Autoencoder (CTSAE), a pioneering unsupervised method for the dimensionality reduction and clustering of gravitational wave glitches.
Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion Model
Demonstrating equivalent generative quality to the software baseline, our system achieved remarkable enhancements in generative speed for both unconditional and conditional generation tasks, by factors of 64. 8 and 156. 5, respectively.
RoNet: Rotation-oriented Continuous Image Translation
The generation of smooth and continuous images between domains has recently drawn much attention in image-to-image (I2I) translation.
Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformer
We propose Deep Longitudinal Targeted Minimum Loss-based Estimation (Deep LTMLE), a novel approach to estimate the counterfactual mean of outcome under dynamic treatment policies in longitudinal problem settings.
GT-Rain Single Image Deraining Challenge Report
This report reviews the results of the GT-Rain challenge on single image deraining at the UG2+ workshop at CVPR 2023.
AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation
We further introduce a Semantic Memory along with a Channel Semantic Grouping strategy to ensure that unlabeled features adequately represent labeled features.
Deep Separable Spatiotemporal Learning for Fast Dynamic Cardiac MRI
This challenge necessitates extensive training data in deep learning reconstruction methods.
Spin: An Efficient Secure Computation Framework with GPU Acceleration
Accuracy and efficiency remain challenges for multi-party computation (MPC) frameworks.
Exploiting Hierarchical Interactions for Protein Surface Learning
In this paper, we present a principled framework based on deep learning techniques, namely Hierarchical Chemical and Geometric Feature Interaction Network (HCGNet), for protein surface analysis by bridging chemical and geometric features with hierarchical interactions.
Digital twin-assisted three-dimensional electrical capacitance tomography for multiphase flow imaging
Three-dimensional electrical capacitance tomography (3D-ECT) has shown promise for visualizing industrial multiphase flows.
Random resistive memory-based deep extreme point learning machine for unified visual processing
Our random resistive memory-based deep extreme point learning machine may pave the way for energy-efficient and training-friendly edge AI across various data modalities and tasks.
Combined Scheduling, Memory Allocation and Tensor Replacement for Minimizing Off-Chip Data Accesses of DNN Accelerators
We propose an optimization framework, named COSMA, for mapping DNNs to an accelerator that finds the optimal operator schedule, memory allocation and tensor replacement that minimizes the additional data accesses.
Pruning random resistive memory for optimizing analogue AI
Here, we report a universal solution, software-hardware co-design using structural plasticity-inspired edge pruning to optimize the topology of a randomly weighted analogue resistive memory neural network.
STOW: Discrete-Frame Segmentation and Tracking of Unseen Objects for Warehouse Picking Robots
Segmentation and tracking of unseen object instances in discrete frames pose a significant challenge in dynamic industrial robotic contexts, such as distribution warehouses.
On the Opportunities of Green Computing: A Survey
To tackle the challenges of computing resources and environmental impact of AI, Green Computing has become a hot research topic.
Kernel Cox partially linear regression: building predictive models for cancer patients' survival
To accurately predict clinical outcomes, it is vital to build an accurate predictive model that relates patients' molecular profiles with patients' survival.
City Foundation Models for Learning General Purpose Representations from OpenStreetMap
This can be attributed to the intrinsic heterogeneity of geospatial data, which encompasses different data types, including points, segments and regions, as well as multiple information modalities, such as a spatial position, visual characteristics and textual annotations.
Prefix-diffusion: A Lightweight Diffusion Model for Diverse Image Captioning
While impressive performance has been achieved in image captioning, the limited diversity of the generated captions and the large parameter scale remain major barriers to the real-word application of these systems.
CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No
Subsequently, we introduce two loss functions: the image-text binary-opposite loss and the text semantic-opposite loss, which we use to teach CLIPN to associate images with no prompts, thereby enabling it to identify unknown samples.
BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions
BLIVA demonstrates significant capability in decoding real-world images, irrespective of text presence.
Context-Aware Pseudo-Label Refinement for Source-Free Domain Adaptive Fundus Image Segmentation
To this end, we propose a context-aware pseudo-label refinement method for SF-UDA.
Morphology-inspired Unsupervised Gland Segmentation via Selective Semantic Grouping
In this paper, we make a first attempt to explore a deep learning method for unsupervised gland segmentation, where no manual annotations are required.
$\ell_p$-Regression in the Arbitrary Partition Model of Communication
We consider the randomized communication complexity of the distributed $\ell_p$-regression problem in the coordinator model, for $p\in (0, 2]$.
Learning the Positions in CountSketch
We fix this issue and propose approaches for learning a sketching matrix for both low-rank approximation and Hessian approximation for second order optimization.
Channel Measurement, Modeling, and Simulation for 6G: A Survey and Tutorial
Then, a survey of the progress of the 6G channel research regarding the above five promising technologies is presented in terms of the latest measurement campaigns, new characteristics, modeling methods, and research prospects.
Evaluating Dynamic Conditional Quantile Treatment Effects with Applications in Ridesharing
However, assessing dynamic quantile treatment effects (QTE) remains a challenge, particularly when dealing with data from ride-sourcing platforms that involve sequential decision-making across time and space.
A Two-Stage Real Image Deraining Method for GT-RAIN Challenge CVPR 2023 Workshop UG$^{\textbf{2}}$+ Track 3
Secondly, a transformer-based single image deraining network Uformer is implemented to pre-train on large real rain dataset and then fine-tuned on pseudo GT to further improve image restoration.
M4Raw: A multi-contrast, multi-repetition, multi-channel MRI k-space dataset for low-field MRI research
This M4Raw dataset will be valuable for the development of advanced data-driven methods specifically for low-field MRI.
SViTT: Temporal Learning of Sparse Video-Text Transformers
Do video-text transformers learn to model temporal relationships across frames?
Ranked #4 on
Video Question Answering
on AGQA 2.0 balanced
(Average Accuracy metric)
Skeleton-based action analysis for ADHD diagnosis
Attention Deficit Hyperactivity Disorder (ADHD) is a common neurobehavioral disorder worldwide.
A Closer Look at the Explainability of Contrastive Language-Image Pre-training
These phenomena conflict with conventional explainability methods based on the class attention map (CAM), where the raw model can highlight the local foreground regions using global supervision without alignment.
Ranked #3 on
Open Vocabulary Semantic Segmentation
on COCO-Stuff-171
(mIoU metric)
Penalized Deep Partially Linear Cox Models with Application to CT Scans of Lung Cancer Patients
The National Lung Screening Trial (NLST) employed computed tomography texture analysis, which provides objective measurements of texture patterns on CT scans, to quantify the mortality risks of lung cancer patients.
CATFL: Certificateless Authentication-based Trustworthy Federated Learning for 6G Semantic Communications
Most existing studies on trustworthy FL aim to eliminate data poisoning threats that are produced by malicious clients, but in many cases, eliminating model poisoning attacks brought by fake servers is also an important objective.
Deep Learning of Semi-Competing Risk Data via a New Neural Expectation-Maximization Algorithm
Prognostication for lung cancer, a leading cause of mortality, remains a complex task, as it needs to quantify the associations of risk factors and health events spanning a patient's entire life.
Spectrograms Are Sequences of Patches
Self-supervised pre-training models have been used successfully in several machine learning domains.
Cross Task Neural Architecture Search for EEG Signal Classifications
Recently, various neural network approaches have been proposed to improve the accuracy of EEG signal recognition.
Asynchronous and Error-prone Longitudinal Data Analysis via Functional Calibration
In many longitudinal settings, time-varying covariates may not be measured at the same time as responses and are often prone to measurement error.
FreeSeg: Free Mask from Interpretable Contrastive Language-Image Pretraining for Semantic Segmentation
We call the proposed framework as FreeSeg, where the mask is freely available from raw feature map of pretraining model.
Ranked #6 on
Zero-Shot Semantic Segmentation
on COCO-Stuff
Tree-based Text-Vision BERT for Video Search in Baidu Video Advertising
How to pair the video ads with the user search is the core task of Baidu video advertising.
Exploring Visual Interpretability for Contrastive Language-Image Pre-training
For this problem, we propose the Explainable Contrastive Language-Image Pre-training (ECLIP), which corrects the explainability via the Masked Max Pooling.
SSORN: Self-Supervised Outlier Removal Network for Robust Homography Estimation
In this paper, we attempt to build a deep learning model that mimics all four steps in the traditional homography estimation pipeline.
CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement
While category-level 9DoF object pose estimation has emerged recently, previous correspondence-based or direct regression methods are both limited in accuracy due to the huge intra-category variances in object shape and color, etc.
Online Active Regression
Active regression considers a linear regression problem where the learner receives a large number of data points but can only observe a small number of labels.
Online Easy Example Mining for Weakly-supervised Gland Segmentation from Histology Images
Existing weakly-supervised semantic segmentation methods in computer vision achieve degenerative results for gland segmentation, since the characteristics and problems of glandular datasets are different from general object datasets.
VALHALLA: Visual Hallucination for Machine Translation
In particular, given a source sentence an autoregressive hallucination transformer is used to predict a discrete visual representation from the input text, and the combined text and hallucinated representations are utilized to obtain the target translation.
GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis
In this paper, we combine the above two paradigms together and propose a novel Generalizable Logic Synthesis (GALOIS) framework to synthesize hierarchical and strict cause-effect logic programs.
UNet#: A UNet-like Redesigning Skip Connections for Medical Image Segmentation
As an essential prerequisite for developing a medical intelligent assistant system, medical image segmentation has received extensive research and concentration from the neural network community.
Lassoed Tree Boosting
Gradient boosting performs exceptionally in most prediction problems and scales well to large datasets.
Multi-task Learning for Gaussian Graphical Regressions with High Dimensional Covariates
Gaussian graphical regression is a powerful means that regresses the precision matrix of a Gaussian graphical model on covariates, permitting the numbers of the response variables and covariates to far exceed the sample size.
Individualized Risk Assessment of Preoperative Opioid Use by Interpretable Neural Network Regression
Preoperative opioid use has been reported to be associated with higher preoperative opioid demand, worse postoperative outcomes, and increased postoperative healthcare utilization and expenditures.
WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma
According to the technical reports of the top-tier teams, CAM is still the most popular approach in WSSS.
Data Augmentation
Weakly supervised Semantic Segmentation
+1
Unsupervised Image Deraining: Optimization Model Driven Deep CNN
Consequently, we design an optimization model-driven deep CNN in which the unsupervised loss function of the optimization model is enforced on the proposed network for better generalization.
PEAR: Personalized Re-ranking with Contextualized Transformer for Recommendation
Specifically, PEAR not only captures feature-level and item-level interactions, but also models item contexts from both the initial ranking list and the historical clicked item list.
Artistic Style Discovery With Independent Components
Style transfer has been well studied in recent years with excellent performance processed.
Physically Disentangled Intra- and Inter-Domain Adaptation for Varicolored Haze Removal
Consequently, we perform inter-domain adaptation between the synthetic and real images by mutually exchanging the background and other two components.
Improving Video Model Transfer With Dynamic Representation Learning
DRL is then formulated as an adversarial learning problem between the video and spatial models, with the objective of maximizing the dynamic score of learned spatiotemporal classifier.
Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation
So we try to improve WSSS in the aspect of noise mitigation.
Ranked #24 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning
A dataset of crowd scenes with people annotations under a bird's eye view (BEV) and ground truth for metric distances is introduced, and several measures for the evaluation of social distance detection systems are proposed.
Pseudo-mask Matters in Weakly-supervised Semantic Segmentation
For these matters, we propose the following designs to push the performance to new state-of-art: (i) Coefficient of Variation Smoothing to smooth the CAMs adaptively; (ii) Proportional Pseudo-mask Generation to project the expanded CAMs to pseudo-mask based on a new metric indicating the importance of each class on each location, instead of the scores trained from binary classifiers.
Ranked #28 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Learning to Cluster via Same-Cluster Queries
We study the problem of learning to cluster data points using an oracle which can answer same-cluster queries.
Inference for High Dimensional Censored Quantile Regression
To our knowledge, there is little work available to draw inference on the effects of high dimensional predictors for censored quantile regression.
Single Pass Entrywise-Transformed Low Rank Approximation
A natural way to do this would be to simply apply $f$ to each entry of $A$, and then compute the matrix decomposition, but this requires storing all of $A$ as well as multiple passes over its entries.
Improvement of image classification by multiple optical scattering
Multiple optical scattering occurs when light propagates in a non-uniform medium.
Deep-learning-based Hyperspectral imaging through a RGB camera
Hyperspectral image (HSI) contains both spatial pattern and spectral information which has been widely used in food safety, remote sensing, and medical detection.
Cross-Lingual Transfer Learning for Statistical Type Inference
Hitherto statistical type inference systems rely thoroughly on supervised learning approaches, which require laborious manual effort to collect and label large amounts of data.
Global and Local Contrastive Self-Supervised Learning for Semantic Segmentation of HR Remote Sensing Images
Supervised learning for semantic segmentation requires a large number of labeled samples, which is difficult to obtain in the field of remote sensing.
Ensemble machine learning approach for screening of coronary heart disease based on echocardiography and risk factors
Background: Extensive clinical evidence suggests that a preventive screening of coronary heart disease (CHD) at an earlier stage can greatly reduce the mortality rate.
More Separable and Easier to Segment: A Cluster Alignment Method for Cross-Domain Semantic Segmentation
Feature alignment between domains is one of the mainstream methods for Unsupervised Domain Adaptation (UDA) semantic segmentation.
Learning-Augmented Sketches for Hessians
We show how to design learned sketches for the Hessian in the context of second order methods.
Growth and site-specific organization of micron-scale biomolecular devices on living mammalian cells
Mesoscale molecular assemblies on the cell surface, such as cilia and filopodia, integrate information, control transport and amplify signals.
Learning Discrete Adaptive Receptive Fields for Graph Convolutional Networks
To address this weakness, we introduce a novel framework of conducting graph convolutions, where nodes are discretely selected among multi-hop neighborhoods to construct adaptive receptive fields (ARFs).
Towards Impartial Multi-task Learning
Multi-task learning (MTL) has been widely used in representation learning.
Modified Gaussian Process Regression Models for Cyclic Capacity Prediction of Lithium-ion Batteries
Experimental results demonstrate that the modified Gaussian process regression model considering the battery electrochemical and empirical ageing signature outperforms other counterparts and is able to achieve satisfactory results for both one-step and multi-step predictions.
Comments on large central charge $T\bar{T}$ deformed conformal field theory and cutoff AdS holography
For a modified version of cutoff AdS holography which is supposed to work only in the sector of classical pure gravity, we show that the flow equation of the metric and one point function of energy-momentum tensor in $T\bar{T}$ deformation corresponds to the flow equation of the boundary metric and Brown-York tensor on a cutoff surface in AdS space as the cutoff surface moves in the direction of normal geodesics.
High Energy Physics - Theory
Anomalous Hall and Nernst Effects in FeRh
Antiferromagnets with tunable phase transitions are promising for future spintronics applications.
Materials Science
Robust Flat Bands with Tunable Energies in Honeycomb Superlattices
Flat bands in lattice models have provided useful platforms for studying strong correlation and topological physics.
Mesoscale and Nanoscale Physics Strongly Correlated Electrons
Distinguishing limit of Bell states for any $n$-photon $D$-dimensional hyperentanglement
There is a maximum number of distinguished Bell states, i. e. distinguising limit which is very important for increasing the channel capacity of quantum communications.
Quantum Physics
Lets Play Music: Audio-driven Performance Video Generation
We propose a new task named Audio-driven Per-formance Video Generation (APVG), which aims to synthesizethe video of a person playing a certain instrument guided bya given music audio clip.
Learning Representations from Audio-Visual Spatial Alignment
To learn from these spatial cues, we tasked a network to perform contrastive audio-visual spatial alignment of 360{\deg} video and spatial audio.
An Adversarial Attack Defending System for Securing In-Vehicle Networks
In a modern vehicle, there are over seventy Electronics Control Units (ECUs).
Streaming Complexity of SVMs
We show that, for both problems, for dimensions $d=1, 2$, one can obtain streaming algorithms with space polynomially smaller than $\frac{1}{\lambda\epsilon}$, which is the complexity of SGD for strongly convex functions like the bias-regularized SVM, and which is known to be tight in general, even for $d=1$.
Graph Structural-topic Neural Network
Specifically, we build topic models upon graphs using anonymous walks and Graph Anchor LDA, an LDA variant that selects significant structural patterns first, so as to alleviate the complexity and generate structural topics efficiently.
Nearly Linear Row Sampling Algorithm for Quantile Regression
We give a row sampling algorithm for the quantile loss function with sample complexity nearly linear in the dimensionality of the data, improving upon the previous best algorithm whose sampling complexity has at least cubic dependence on the dimensionality.
Background Data Resampling for Outlier-Aware Classification
The problem of learning an image classifier that allows detection of out-of-distribution (OOD) examples, with the help of auxiliary background datasets, is studied.
Weakly Supervised Lesion Localization With Probabilistic-CAM Pooling
Localizing thoracic diseases on chest X-ray plays a critical role in clinical practices such as diagnosis and treatment planning.
Learning-Augmented Data Stream Algorithms
For estimating the $p$-th frequency moment for $0 < p < 2$ we obtain the first algorithms with optimal update time.
Cosmetic-Aware Makeup Cleanser
Face verification aims at determining whether a pair of face images belongs to the same identity.
Viral Pneumonia Screening on Chest X-ray Images Using Confidence-Aware Anomaly Detection
In this paper, we formulate the task of differentiating viral pneumonia from non-viral pneumonia and healthy controls into an one-class classification-based anomaly detection problem, and thus propose the confidence-aware anomaly detection (CAAD) model, which consists of a shared feature extractor, an anomaly detection module, and a confidence prediction module.
Informative Sample Mining Network for Multi-Domain Image-to-Image Translation
The performance of multi-domain image-to-image translation has been significantly improved by recent progress in deep generative models.
Exploiting Style and Attention in Real-World Super-Resolution
Real-world image super-resolution (SR) is a challenging image translation problem.
Evolving ab initio trading strategies in heterogeneous environments
Securities markets are quintessential complex adaptive systems in which heterogeneous agents compete in an attempt to maximize returns.
OpenArray v1.0: a simple operator library for the decoupling of ocean modeling and parallel computing
In this work, we design a simple computing library to bridge the gap and decouple the work of ocean modeling from parallel computing.
Path Planning Games
Path planning is a fundamental and extensively explored problem in robotic control.
Directed-Weighting Group Lasso for Eltwise Blocked CNN Pruning
Eltwise layer is a commonly used structure in the multi-branch deep learning network.
Cross-Spectral Face Hallucination via Disentangling Independent Factors
The cross-sensor gap is one of the challenges that have aroused much research interests in Heterogeneous Face Recognition (HFR).
Data-Driven Neuron Allocation for Scale Aggregation Networks
The most informative output neurons in each block are preserved while others are discarded, and thus neurons for multiple scales are competitively and adaptively allocated.
Ranked #763 on
Image Classification
on ImageNet
REPAIR: Removing Representation Bias by Dataset Resampling
An experimental set-up is also introduced to measure the bias of any dataset for a given representation, and the impact of this bias on the performance of recognition models.
Biphasic Learning of GANs for High-Resolution Image-to-Image Translation
In this work, we present a novel training framework for GANs, namely biphasic learning, to achieve image-to-image translation in multiple visual domains at $1024^2$ resolution.
Estimation and Inference for High Dimensional Generalized Linear Models: A Splitting and Smoothing Approach
In modern biomedical studies, focus has been shifted to estimate and explain the joint effects of high dimensional predictors (for example, molecular biomarkers) on a disease outcome (for example, onset of cancer).
Methodology
Detecting Lesion Bounding Ellipses With Gaussian Proposal Networks
Instead of directly regressing the rotation angle of the ellipse as the common practice, GPN represents bounding ellipses as 2D Gaussian distributions on the image plain and minimizes the Kullback-Leibler (KL) divergence between the proposed Gaussian and the ground truth Gaussian for object localization.
A Survey of Deep Facial Attribute Analysis
Deep learning based facial attribute analysis consists of two basic sub-issues: facial attribute estimation (FAE), which recognizes whether facial attributes are present in given images, and facial attribute manipulation (FAM), which synthesizes or removes desired facial attributes.
Arbitrary Talking Face Generation via Attentional Audio-Visual Coherence Learning
Talking face generation aims to synthesize a face video with precise lip synchronization as well as a smooth transition of facial motion over the entire video via the given speech clip and facial image.
DeepCruiser: Automated Guided Testing for Stateful Deep Learning Systems
Our in-depth evaluation on a state-of-the-art speech-to-text DL system demonstrates the effectiveness of our technique in improving quality and reliability of stateful DL systems.
Testing Matrix Rank, Optimally
This improves upon the previous $O(d^2/\epsilon^2)$ bound (SODA'03), and bypasses an $\Omega(d^2/\epsilon^2)$ lower bound of (KDD'14) which holds if the algorithm is required to read a submatrix.
RESOUND: Towards Action Recognition without Representation Bias
The notion of the representation bias of a dataset is proposed to combat this problem.
Large Margin Neural Language Model
We propose a large margin criterion for training neural language models.
Cancer Metastasis Detection With Neural Conditional Random Field
Compared to the baseline method without considering spatial correlations, we show that the proposed NCRF framework obtains probability maps of patch predictions with better visual quality.
Covariance-Insured Screening
Modern bio-technologies have produced a vast amount of high-throughput data with the number of predictors far greater than the sample size.
DeepIM: Deep Iterative Matching for 6D Pose Estimation
Estimating the 6D pose of objects from images is an important problem in various applications such as robot manipulation and virtual reality.
Ranked #3 on
6D Pose Estimation using RGBD
on YCB-Video
Enhanced Biologically Inspired Model for Image Recognition Based on a Novel Patch Selection Method with Moment
Although the performance of BIM for image recognition is robust, it takes the randomly selected ways for the patch selection, which is sightless, and results in heavy computing burden.
Anti-Makeup: Learning A Bi-Level Adversarial Network for Makeup-Invariant Face Verification
This paper proposes a learning from generation approach for makeup-invariant face verification by introducing a bi-level adversarial network (BLAN).
Exploring Neural Transducers for End-to-End Speech Recognition
In this work, we perform an empirical comparison among the CTC, RNN-Transducer, and attention-based Seq2Seq models for end-to-end speech recognition.
Consensus measure of rankings
The consensus measure can be used to evaluate rankings in many information systems, as quite often there is not ground truth available for evaluation.
Deformable Convolutional Networks
Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules.
Ranked #3 on
Vessel Detection
on Vessel detection Dateset
Robust and Real-time Deep Tracking Via Multi-Scale Domain Adaptation
Visual tracking is a fundamental problem in computer vision.
Fully Convolutional Instance-aware Semantic Segmentation
It inherits all the merits of FCNs for semantic segmentation and instance mask proposal.
Ranked #100 on
Instance Segmentation
on COCO test-dev
Classification with Ultrahigh-Dimensional Features
Although much progress has been made in classification with high-dimensional features \citep{Fan_Fan:2008, JGuo:2010, CaiSun:2014, PRXu:2014}, classification with ultrahigh-dimensional features, wherein the features much outnumber the sample size, defies most existing work.
R-FCN: Object Detection via Region-based Fully Convolutional Networks
In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almost all computation shared on the entire image.
Ranked #4 on
Real-Time Object Detection
on PASCAL VOC 2007
Instance-sensitive Fully Convolutional Networks
In contrast to the previous FCN that generates one score map, our FCN is designed to compute a small set of instance-sensitive score maps, each of which is the outcome of a pixel-wise classifier of a relative position to instances.
Neural Self Talk: Image Understanding via Continuous Questioning and Answering
In this paper we consider the problem of continuously discovering image contents by actively asking image based questions and subsequently answering the questions being asked.
Compositional Memory for Visual Question Answering
We then feed the episodes to a standard question answering module together with the contextual visual information and linguistic information.
Free-hand Sketch Synthesis with Deformable Stroke Models
We present a generative model which can automatically summarize the stroke composition of free-hand sketches of a given category.
Grasp Type Revisited: A Modern Perspective on a Classical Feature for Vision
The grasp type provides crucial information about human action.
Making Better Use of Edges via Perceptual Grouping
We propose a perceptual grouping framework that organizes image edges into meaningful structures and demonstrate its usefulness on various computer vision tasks.
Sketch-based 3D Shape Retrieval using Convolutional Neural Networks
Almost always in state of the art approaches a large amount of "best views" are computed for 3D models, with the hope that the query sketch matches one of these 2D projections of 3D models using predefined features.
DeepTrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking
In this work, we present an efficient and very robust tracking algorithm using a single Convolutional Neural Network (CNN) for learning effective feature representations of the target object, in a purely online manner.
Random Bits Regression: a Strong General Predictor for Big Data
To improve accuracy and speed of regressions and classifications, we present a data-based prediction method, Random Bits Regression (RBR).
Physical Computing With No Clock to Implement the Gaussian Pyramid of SIFT Algorithm
In this paper, we propose an active circuit network to implement multi-scale Gaussian filter, which is also called Gaussian Pyramid in image preprocessing.
Is Rotation a Nuisance in Shape Recognition?
and 3) how to use rotation unaware local features for rotation aware shape recognition?
Convolutional Neural Networks for No-Reference Image Quality Assessment
In this work we describe a Convolutional Neural Network (CNN) to accurately predict image quality without a reference image.
Orientation Robust Text Line Detection in Natural Images
In this paper, higher-order correlation clustering (HOCC) is used for text line detection in natural images.
Beyond Physical Connections: Tree Models in Human Pose Estimation
Our method outperformed the state of the art on the LSP, both in the scenarios when the training images are from the same dataset and from the PARSE dataset.
Learning Visual Symbols for Parsing Human Poses in Images
When the structure of the compositional parts is a tree, we derive an efficient approach to estimating human poses in images.
