Search Results for author:
Found 301 papers, 110 papers with code
FreeAnchor: Learning to Match Anchors for Visual Object Detection
In this study, we propose a learning-to-match approach to break IoU restriction, allowing objects to match anchors in a flexible manner.
Ranked #125 on
Object Detection
on COCO test-dev
Learning to Match Distributions for Domain Adaptation
However, it remains challenging to determine which method is suitable for a given application since they are built with certain priors or bias.
Generalizing to Unseen Domains: A Survey on Domain Generalization
Domain generalization deals with a challenging setting where one or several different but related domain(s) are given, and the goal is to learn a model that can generalize to an unseen test domain.
Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection
It employs a "divide-and-conquer" strategy and separately exploits positives for the classification and localization task, which is more robust to the assignment ambiguity.
Ranked #1 on
Semi-Supervised Object Detection
on COCO 10% labeled data
(detector metric)
VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results
Results of 33 object detection algorithms are presented.
FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-shot Subject-Driven Generation
In this paper, motivated by object-oriented programming, we model the subject as a derived class whose base class is its semantic category.
Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection
In this paper, we propose a novel unified relational reasoning graph network for arbitrary shape text detection.
Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets
This technical note describes the recent updates of Graphormer, including architecture design modifications, and the adaption to 3D molecular dynamics simulation.
Beyond Bounding-Box: Convex-Hull Feature Adaptation for Oriented and Densely Packed Object Detection
Detecting oriented and densely packed objects remains challenging for spatial feature aliasing caused by the intersection of reception fields between objects.
Ranked #34 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
Existing state-of-the-art approaches rely on reinforcement learning to reward the decoder when it generates any of the equivalent serializations.
Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching
As such, the agent can finish inlier matching timely when the affinity score stops growing, for which otherwise an additional parameter i. e. the number of inliers is needed to avoid matching outliers.
PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior
Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of the data density.
CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario
The most commonly used open-source traffic simulator SUMO is, however, not scalable to large road network and large traffic flow, which hinders the study of reinforcement learning on traffic scenarios.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
GRES: Generalized Referring Expression Segmentation
Existing classic RES datasets and methods commonly support single-target expressions only, i. e., one expression refers to one target object.
Generalized Referring Expression Segmentation
Referring Expression
+1
Invertible Image Rescaling
High-resolution digital images are usually downscaled to fit various display screens or save the cost of storage and bandwidth, meanwhile the post-upscaling is adpoted to recover the original resolutions or the details in the zoom-in images.
Invertible Rescaling Network and Its Extensions
To be specific, we develop invertible models to generate valid degraded images and meanwhile transform the distribution of lost contents to the fixed distribution of a latent variable during the forward degradation.
Image as Set of Points
Context clusters (CoCs) view an image as a set of unorganized points and extract features via simplified clustering algorithm.
MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions
To investigate the feasibility of using motion expressions to ground and segment objects in videos, we propose a large-scale dataset called MeViS, which contains numerous motion expressions to indicate target objects in complex environments.
Ranked #2 on
Referring Video Object Segmentation
on MeViS
Vision-Language Transformer and Query Generation for Referring Segmentation
We introduce transformer and multi-head attention to build a network with an encoder-decoder attention mechanism architecture that "queries" the given image with the language expression.
Generalized Referring Expression Comprehension
Generalized Referring Expression Segmentation
+1
VLT: Vision-Language Transformer and Query Generation for Referring Segmentation
We propose a Vision-Language Transformer (VLT) framework for referring segmentation to facilitate deep interactions among multi-modal information and enhance the holistic understanding to vision-language features.
Ranked #3 on
Referring Video Object Segmentation
on MeViS
Referring Expression Segmentation
Referring Video Object Segmentation
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
In this work, we consider a new type of attacks, called backdoor attacks, where the attacker's goal is to create a backdoor into a learning-based authentication system, so that he can easily circumvent the system by leveraging the backdoor.
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
However, since the target objects in these existing datasets are usually relatively salient, dominant, and isolated, VOS under complex scenes has rarely been studied.
HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment
Existing face restoration researches typically relies on either the degradation prior or explicit guidance labels for training, which often results in limited generalization ability over real-world images with heterogeneous degradations and rich background contents.
Prototype Mixture Models for Few-shot Semantic Segmentation
Few-shot segmentation is challenging because objects within the support and query images could significantly differ in appearance and pose.
GREC: Generalized Referring Expression Comprehension
This dataset encompasses a range of expressions: those referring to multiple targets, expressions with no specific target, and the single-target expressions.
Generalized Referring Expression Comprehension
Referring Expression
+1
Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models
Generative models have recently exhibited exceptional capabilities in text-to-image generation, but still struggle to generate image sequences coherently.
Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detection
The problem of cross-platform binary code similarity detection aims at detecting whether two binary functions coming from different platforms are similar or not.
Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train
Foundation models have exhibited remarkable success in various applications, such as disease diagnosis and text report generation.
Shotgun crystal structure prediction using machine-learned formation energies
Stable or metastable crystal structures of assembled atoms can be predicted by finding the global or local minima of the energy surface defined on the space of the atomic configurations.
Adaptive Linear Span Network for Object Skeleton Detection
Conventional networks for object skeleton detection are usually hand-crafted.
Towards Real-World Burst Image Super-Resolution: Benchmark and Method
Despite substantial advances, single-image super-resolution (SISR) is always in a dilemma to reconstruct high-quality images with limited information from one input image, especially in realistic scenarios.
DiffusionRet: Generative Text-Video Retrieval with Diffusion Model
Existing text-video retrieval solutions are, in essence, discriminant models focused on maximizing the conditional likelihood, i. e., p(candidates|query).
Ranked #15 on
Video Retrieval
on MSVD
Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning
Contrastive learning-based video-language representation learning approaches, e. g., CLIP, have achieved outstanding performance, which pursue semantic interaction upon pre-defined video-text pairs.
Ranked #8 on
Video Question Answering
on MSRVTT-QA
Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment
In this paper, we propose the Disentangled Conceptualization and Set-to-set Alignment (DiCoSA) to simulate the conceptualizing and reasoning process of human beings.
Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images
By contrast, it is hard to collect paired data for in-the-wild scenes, and therefore, virtual try-on for casual images of people with more diverse poses against cluttered backgrounds is rarely studied.
Ranked #1 on
Virtual Try-on
on StreetTryOn
CounTR: Transformer-based Generalised Visual Counting
In this paper, we consider the problem of generalised visual object counting, with the goal of developing a computational model for counting the number of objects from arbitrary semantic categories, using arbitrary number of "exemplars", i. e. zero-shot or few-shot counting.
Ranked #3 on
Object Counting
on FSC147
Learning Causal Semantic Representation for Out-of-Distribution Prediction
Conventional supervised learning methods, especially deep ones, are found to be sensitive to out-of-distribution (OOD) examples, largely because the learned representation mixes the semantic factor with the variation factor due to their domain-specific correlation, while only the semantic factor causes the output.
Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection
Few-shot object detection has made substantial progressby representing novel class objects using the feature representation learned upon a set of base class objects.
Ranked #14 on
Few-Shot Object Detection
on MS-COCO (10-shot)
C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
Weakly supervised object detection (WSOD) is a challenging task when provided with image category supervision but required to simultaneously learn object locations and object detectors.
Delving into Transferable Adversarial Examples and Black-box Attacks
In this work, we are the first to conduct an extensive study of the transferability over large models and a large scale dataset, and we are also the first to study the transferability of targeted adversarial examples with their target labels.
Frame Flexible Network
To fix this issue, we propose a general framework, named Frame Flexible Network (FFN), which not only enables the model to be evaluated at different frames to adjust its computation, but also reduces the memory costs of storing multiple models significantly.
Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
As machine learning becomes widely used for automated decisions, attackers have strong incentives to manipulate the results and models generated by machine learning algorithms.
On the Generative Utility of Cyclic Conditionals
This is motivated by the observation that deep generative models, in addition to a likelihood model $p(x|z)$, often also use an inference model $q(z|x)$ for extracting representation, but they rely on a usually uninformative prior distribution $p(z)$ to define a joint distribution, which may render problems like posterior collapse and manifold mismatch.
Direct Molecular Conformation Generation
Molecular conformation generation aims to generate three-dimensional coordinates of all the atoms in a molecule and is an important task in bioinformatics and pharmacology.
A Systematic Review of Deep Learning-based Research on Radiology Report Generation
Specifically, we firstly cover pivotal RRG approaches based on the task-specific features of radiographs, reports, and the cross-modal relations between them, and then illustrate the benchmark datasets conventionally used for this task with evaluation metrics, subsequently analyze the performance of different approaches and finally offer our summary on the challenges and the trends in future directions.
PolSAR Image Classification Based on Dilated Convolution and Pixel-Refining Parallel Mapping network in the Complex Domain
For general supervised deep learning classification algorithms, the pixel-by-pixel algorithm achieves precise yet inefficient classification with a small number of labeled pixels, whereas the pixel mapping algorithm achieves efficient yet edge-rough classification with more prior labels required.
Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning
The generative perception model acts as a feature decoder to focus on comprehending high temporal resolution and short-term representation by introducing a motion-attention mechanism.
Learning to Respond with Stickers: A Framework of Unifying Multi-Modality in Multi-Turn Dialog
Stickers with vivid and engaging expressions are becoming increasingly popular in online messaging apps, and some works are dedicated to automatically select sticker response by matching text labels of stickers with previous utterances.
Deep Residual Learning for Channel Estimation in Intelligent Reflecting Surface-Assisted Multi-User Communications
To this end, we first develop a versatile DReL-based channel estimation framework where a deep residual network (DRN)-based MMSE estimator is derived in terms of Bayesian philosophy.
Deep Residual Network Empowered Channel Estimation for IRS-Assisted Multi-User Communication Systems
Channel estimation is of great importance in realizing practical intelligent reflecting surface-assisted multi-user communication (IRS-MC) systems.
Regularizing Face Verification Nets For Pain Intensity Regression
In this way, the expression intensity regression task can benefit from the rich feature representations trained on a huge amount of data for face verification.
SsciBERT: A Pre-trained Language Model for Social Science Texts
The academic literature of social sciences records human civilization and studies human social problems.
Noise-resistant Deep Metric Learning with Ranking-based Instance Selection
The existence of noisy labels in real-world data negatively impacts the performance of deep learning models.
Towards Generating Real-World Time Series Data
In this paper, we propose a novel generative framework for RTS data - RTSGAN to tackle the aforementioned challenges.
Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition
The goal of this work is to develop a more reliable technique that can carry out an end-to-end evaluation of adversarial robustness for commercial systems.
Multimodal Transformer for Automatic 3D Annotation and Object Detection
By enriching the sparse point clouds, our method achieves 4. 48\% and 4. 03\% better 3D AP on KITTI moderate and hard samples, respectively, versus the state-of-the-art autolabeler.
Late-Constraint Diffusion Guidance for Controllable Image Synthesis
Specifically, we train a lightweight condition adapter to establish the correlation between external conditions and internal representations of diffusion models.
Ranked #1 on
Conditional Text-to-Image Synthesis
on COCO 2017 val
Conditional Image Generation
Conditional Text-to-Image Synthesis
Open-set Text Recognition via Character-Context Decoupling
Contextual information can be decomposed into temporal information and linguistic information.
Watermarking Text Generated by Black-Box Language Models
To allow third-parties to autonomously inject watermarks into generated text, we develop a watermarking framework for black-box language model usage scenarios.
Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning
Behavioral cloning has proven to be effective for learning sequential decision-making policies from expert demonstrations.
Recovering Latent Causal Factor for Generalization to Distributional Shifts
To avoid such a spurious correlation, we propose \textbf{La}tent \textbf{C}ausal \textbf{I}nvariance \textbf{M}odels (LaCIM) that specifies the underlying causal structure of the data and the source of distributional shifts, guiding us to pursue only causal factor for prediction.
Unrestricted Adversarial Attacks on ImageNet Competition
Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input.
ParCo: Part-Coordinating Text-to-Motion Synthesis
However, these methods encounter challenges such as the lack of coordination between different part motions and difficulties for networks to understand part concepts.
Ranked #8 on
Motion Synthesis
on HumanML3D
Understanding and Accelerating Particle-Based Variational Inference
Particle-based variational inference methods (ParVIs) have gained attention in the Bayesian inference literature, for their capacity to yield flexible and accurate approximations.
Discretization-Aware Architecture Search
The search cost of neural architecture search (NAS) has been largely reduced by weight-sharing methods.
Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning
We argue that an overlooked problem of robust SSL is its corrupted information on semantic level, practically limiting the development of the field.
Towards Interactive Image Inpainting via Sketch Refinement
To address this problem, we propose a two-stage image inpainting method termed SketchRefiner.
FreestyleRet: Retrieving Images from Style-Diversified Queries
In this paper, we propose the Style-Diversified Query-Based Image Retrieval task, which enables retrieval based on various query styles.
6GAN: IPv6 Multi-Pattern Target Generation via Generative Adversarial Nets with Reinforcement Learning
6GAN forces multiple generators to train with a multi-class discriminator and an alias detector to generate non-aliased active targets with different addressing pattern types.
ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation
This paper studies Semi-Supervised Domain Adaptation (SSDA), a practical yet under-investigated research topic that aims to learn a model of good performance using unlabeled samples and a few labeled samples in the target domain, with the help of labeled samples from a source domain.
Crystal structure prediction with machine learning-based element substitution
The prediction of energetically stable crystal structures formed by a given chemical composition is a central problem in solid-state physics.
Proposal Distribution Calibration for Few-Shot Object Detection
Adapting object detectors learned with sufficient supervision to novel classes under low data regimes is charming yet challenging.
Instance Brownian Bridge as Texts for Open-vocabulary Video Instance Segmentation
To mold instance queries to follow Brownian bridge and accomplish alignment with class texts, we design Bridge-Text Alignment (BTA) to learn discriminative bridge-level representations of instances via contrastive objectives.
DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment
We applied our proposed approach to two real-world food image data sets (UEC-256 and Food-101) and achieved impressive results.
SiamHAN: IPv6 Address Correlation Attacks on TLS Encrypted Traffic via Siamese Heterogeneous Graph Attention Network
To do this, we propose an IPv6 address correlation model - SiamHAN.
LaPE: Layer-adaptive Position Embedding for Vision Transformers with Independent Layer Normalization
A typical way to introduce position information is adding the absolute Position Embedding (PE) to patch embedding before entering VTs.
Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning
Concretely, by estimating a transition matrix that captures the probability of one class being confused with another, an instruction containing a correct exemplar and an erroneous one from the most probable noisy class can be constructed.
Understanding MCMC Dynamics as Flows on the Wasserstein Space
It is known that the Langevin dynamics used in MCMC is the gradient flow of the KL divergence on the Wasserstein space, which helps convergence analysis and inspires recent particle-based variational inference methods (ParVIs).
Position-Aware Subgraph Neural Networks with Data-Efficient Learning
2) Prevailing graph augmentation methods for GEL, including rule-based, sample-based, adaptive, and automated methods, are not suitable for augmenting subgraphs because a subgraph contains fewer nodes but richer information such as position, neighbor, and structure.
Enhancing Intrinsic Adversarial Robustness via Feature Pyramid Decoder
Whereas adversarial training is employed as the main defence strategy against specific adversarial samples, it has limited generalization capability and incurs excessive time complexity.
Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning
As a proxy task, it converts rich self-supervised representations into video clip operations (options), which enhances the flexibility and reduces the complexity of representation learning.
Ranked #11 on
Self-supervised Video Retrieval
on HMDB51
Disjoint Masking with Joint Distillation for Efficient Masked Image Modeling
Masked image modeling (MIM) has shown great promise for self-supervised learning (SSL) yet been criticized for learning inefficiency.
Evaluating Large Language Models on Graphs: Performance Insights and Comparative Analysis
Yet, the application of LLMs to graph data remains under-explored.
Predicting Solar Flares Using a Long Short-Term Memory Network
The essence of our approach is to model data samples in an AR as time series and use LSTMs to capture temporal information of the data samples.
UATVR: Uncertainty-Adaptive Text-Video Retrieval
In the refined embedding space, we represent text-video pairs as probabilistic distributions where prototypes are sampled for matching evaluation.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
TANet: Transformer-based Asymmetric Network for RGB-D Salient Object Detection
We employ the powerful feature extraction capability of Transformer (PVTv2) to extract global semantic information from RGB data and design a lightweight CNN backbone (LWDepthNet) to extract spatial structure information from depth data without pre-training.
Test-time Fourier Style Calibration for Domain Generalization
Thus, it is still possible that those methods can overfit to source domains and perform poorly on target domains.
Distilling Representations from GAN Generator via Squeeze and Span
In recent years, generative adversarial networks (GANs) have been an actively studied topic and shown to successfully produce high-quality realistic images in various domains.
Sampling with Mirrored Stein Operators
We introduce a new family of particle evolution samplers suitable for constrained domains and non-Euclidean geometries.
Multi-Granularity Structural Knowledge Distillation for Language Model Compression
Transferring the knowledge to a small model through distillation has raised great interest in recent years.
Adaptive Region Selection for Active Learning in Whole Slide Image Semantic Segmentation
We find that the efficiency of this method highly depends on the choice of AL step size (i. e., the combination of region size and the number of selected regions per WSI), and a suboptimal AL step size can result in redundant annotation requests or inflated computation costs.
Riemannian Stein Variational Gradient Descent for Bayesian Inference
The benefits are two-folds: (i) for inference tasks in Euclidean spaces, RSVGD has the advantage over SVGD of utilizing information geometry, and (ii) for inference tasks on Riemann manifolds, RSVGD brings the unique advantages of SVGD to the Riemannian world.
ILSGAN: Independent Layer Synthesis for Unsupervised Foreground-Background Segmentation
Unsupervised foreground-background segmentation aims at extracting salient objects from cluttered backgrounds, where Generative Adversarial Network (GAN) approaches, especially layered GANs, show great promise.
SCNet: A Neural Network for Automated Side-Channel Attack
Information about system characteristics such as power consumption, electromagnetic leaks and sound can be exploited by the side-channel attack to compromise the system.
Identifying and Tracking Solar Magnetic Flux Elements with Deep Learning
Deep learning has drawn a lot of interest in recent years due to its effectiveness in processing big and complex observational data gathered from diverse instruments.
Bayesian multi-exposure image fusion for robust high dynamic range ptychography
Image information is restricted by the dynamic range of the detector, which can be addressed using multi-exposure image fusion (MEF).
Predicting Coronal Mass Ejections Using SDO/HMI Vector Magnetic Data Products and Recurrent Neural Networks
We present two recurrent neural networks (RNNs), one based on gated recurrent units and the other based on long short-term memory, for predicting whether an active region (AR) that produces an M- or X-class flare will also produce a coronal mass ejection (CME).
Feature-Gate Coupling for Dynamic Network Pruning
Gating modules have been widely explored in dynamic network pruning to reduce the run-time computational cost of deep neural networks while preserving the representation of features.
Fast Matrix Multiplication Without Tears: A Constraint Programming Approach
In this work, we propose a simple yet novel Constraint Programming approach to find non-commutative algorithms for fast matrix multiplication or provide proof of infeasibility otherwise.
AIA: Attention in Attention Within Collaborate Domains
Attention mechanisms can effectively improve the performance of the mobile networks with a limited computational complexity cost.
GMTR: Graph Matching Transformers
Meanwhile, on Pascal VOC, QueryTrans improves the accuracy of NGMv2 from $80. 1\%$ to $\mathbf{83. 3\%}$, and BBGM from $79. 0\%$ to $\mathbf{84. 5\%}$.
Ranked #1 on
Graph Matching
on PASCAL VOC
(matching accuracy metric)
Cross-Lingual Low-Resource Set-to-Description Retrieval for Global E-Commerce
We manually collect a new and high-quality paired dataset, where each pair contains an unordered product attribute set in the source language and an informative product description in the target language.
Progressive Cluster Purification for Unsupervised Feature Learning
In this work, we propose a novel clustering based method, which, by iteratively excluding class inconsistent samples during progressive cluster formation, alleviates the impact of noise samples in a simple-yet-effective manner.
DeepSun: Machine-Learning-as-a-Service for Solar Flare Prediction
Solar flare prediction plays an important role in understanding and forecasting space weather.
Human-in-the-loop model explanation via verbatim boundary identification in generated neighborhoods
Our method can be divided into three stages: 1) a neighborhood generation stage, which generates instances based on the given sample; 2) a classification stage, which yields classifications on the generated instances to carve out the local decision boundary and delineate the model behavior; and 3) a human-in-the-loop stage, which involves human to refine and explore the neighborhood of interest.
BIG-bench Machine Learning
Explainable artificial intelligence
+1
Scribble-Supervised Target Extraction Method Based on Inner Structure-Constraint for Remote Sensing Images
Weakly supervised learning based on scribble annotations in target extraction of remote sensing images has drawn much interest due to scribbles' flexibility in denoting winding objects and low cost of manually labeling.
Consisaug: A Consistency-based Augmentation for Polyp Detection in Endoscopy Image Analysis
Colorectal cancer (CRC), which frequently originates from initially benign polyps, remains a significant contributor to global cancer-related mortality.
Message Passing Stein Variational Gradient Descent
Stein variational gradient descent (SVGD) is a recently proposed particle-based Bayesian inference method, which has attracted a lot of interest due to its remarkable approximation ability and particle efficiency compared to traditional variational inference and Markov Chain Monte Carlo methods.
Multi-task Learning for Macromolecule Classification, Segmentation and Coarse Structural Recovery in Cryo-Tomography
Cellular Electron Cryo-Tomography (CECT) is a powerful 3D imaging tool for studying the native structure and organization of macromolecules inside single cells.
Fooling Vision and Language Models Despite Localization and Attention Mechanism
Our work sheds new light on understanding adversarial attacks on vision systems which have a language component and shows that attention, bounding box localization, and compositional internal structures are vulnerable to adversarial attacks.
Learning-Based Dequantization For Image Restoration Against Extremely Poor Illumination
All existing image enhancement methods, such as HDR tone mapping, cannot recover A/D quantization losses due to insufficient or excessive lighting, (underflow and overflow problems).
Towards Synthesizing Complex Programs from Input-Output Examples
In our evaluation, we show that using our novel approach, neural parsing programs can be learned to achieve 100% test accuracy on test inputs that are 500x longer than the training samples.
The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks
This paper describes a testing methodology for quantitatively assessing the risk that rare or unique training-data sequences are unintentionally memorized by generative sequence models---a common type of machine-learning model.
Attentive Tensor Product Learning
This paper proposes a new architecture - Attentive Tensor Product Learning (ATPL) - to represent grammatical structures in deep learning models.
Generating Plans that Predict Themselves
We introduce $t$-\ACty{}: a measure that quantifies the accuracy and confidence with which human observers can predict the remaining robot plan from the overall task goal and the observed initial $t$ actions in the plan.
Deep learning based supervised semantic segmentation of Electron Cryo-Subtomograms
Cellular Electron Cryo-Tomography (CECT) is a powerful imaging technique for the 3D visualization of cellular structure and organization at submolecular resolution.
Tree-to-tree Neural Networks for Program Translation
We observe that program translation is a modular procedure, in which a sub-tree of the source tree is translated into the corresponding target sub-tree at each step.
Goal Inference Improves Objective and Perceived Performance in Human-Robot Collaboration
The study of human-robot interaction is fundamental to the design and use of robotics in real-world applications.
Pragmatic-Pedagogic Value Alignment
In robotics, value alignment is key to the design of collaborative robots that can integrate into human workflows, successfully inferring and adapting to their users' objectives as they go.
Demonstration of Topological Data Analysis on a Quantum Processor
Topological data analysis offers a robust way to extract useful information from noisy, unstructured data by identifying its underlying structure.
Anomaly Detection in Hierarchical Data Streams under Unknown Models
We consider the problem of detecting a few targets among a large number of hierarchical data streams.
MAT: A Multimodal Attentive Translator for Image Captioning
In this way, the sequential representation of an image can be naturally translated to a sequence of words, as the target sequence of the RNN model.
How Much Data is Enough? A Statistical Approach with Case Study on Longitudinal Driving Behavior
For projects that cost millions of dollars, it is critical to determine the right amount of data needed.
Feature Analysis and Selection for Training an End-to-End Autonomous Vehicle Controller Using the Deep Learning Approach
We collect a large set of data using The Open Racing Car Simulator (TORCS) and classify the image features into three categories (sky-related, roadside-related, and road-related features). We then design two experimental frameworks to investigate the importance of each single feature for training a CNN controller. The first framework uses the training data with all three features included to train a controller, which is then tested with data that has one feature removed to evaluate the feature's effects.
Automated Inference on Sociopsychological Impressions of Attractive Female Faces
This article is a sequel to our earlier work [25].
Latent Attention For If-Then Program Synthesis
Automatic translation from natural language descriptions into programs is a longstanding challenging problem.
Robust High-Dimensional Linear Regression
The effectiveness of supervised learning techniques has made them ubiquitous in research and practice.
Feature Selection Based on Confidence Machine
We propose a filter method for unsupervised feature selection which is based on the Confidence Machine.
Latent Feature Based FM Model For Rating Prediction
Rating Prediction is a basic problem in Recommender System, and one of the most widely used method is Factorization Machines(FM).
Linear Span Network for Object Skeleton Detection
Hinted by this, we formalize a Linear Span framework, and propose Linear Span Network (LSN) modified by Linear Span Units (LSUs), which minimize the reconstruction error of convolutional network.
Boosting Model Performance through Differentially Private Model Aggregation
In this work, two approaches for private model aggregation are proposed that enable the transfer of knowledge from existing models trained on other companies' datasets to a new company with limited labeled data while protecting each client company's underlying individual sensitive information.
A Multiscale Image Denoising Algorithm Based On Dilated Residual Convolution Network
To address this issue, here we propose a novel deep residual learning model that combines the dilated residual convolution and multi-scale convolution groups.
Stochastic Gradient Geodesic MCMC Methods
We propose two stochastic gradient MCMC methods for sampling from Bayesian posterior distributions defined on Riemann manifolds with a known geodesic flow, e. g. hyperspheres.
Execution-Guided Neural Program Synthesis
Most existing neural program synthesis approaches employ an encoder-decoder architecture, which uses an encoder to compute the embedding of the given input-output examples, as well as a decoder to generate the program from the embedding following a given syntax.
A Deep Dive into Understanding Tumor Foci Classification using Multiparametric MRI Based on Convolutional Neural Network
Deep learning models have had a great success in disease classifications using large data pools of skin cancer images or lung X-rays.
Segmentation of the Prostatic Gland and the Intraprostatic Lesions on Multiparametic MRI Using Mask-RCNN
Prostate cancer (PCa) is the most common cancer in men in the United States.
Orthogonal Decomposition Network for Pixel-Wise Binary Classification
The weight sharing scheme and spatial pooling operations in Convolutional Neural Networks (CNNs) introduce semantic correlation to neighboring pixels on feature maps and therefore deteriorate their pixel-wise classification performance.
Kingsoft's Neural Machine Translation System for WMT19
This paper describes the Kingsoft AI Lab{'}s submission to the WMT2019 news translation shared task.
Automated Fashion Size Normalization
The ability to accurately predict the fit of fashion items and recommend the correct size is key to reducing merchandise returns in e-commerce.
Generating Persuasive Visual Storylines for Promotional Videos
Video contents have become a critical tool for promoting products in E-commerce.
Distributed representation of patients and its use for medical cost prediction
Efficient representation of patients is very important in the healthcare domain and can help with many tasks such as medical risk prediction.
ALCNN: Attention-based Model for Fine-grained Demand Inference of Dock-less Shared Bike in New Cities
In this paper, we study the problem of inferring fine-grained bike demands anywhere in a new city before the deployment of bikes.
Straight-Through Estimator as Projected Wasserstein Gradient Flow
The Straight-Through (ST) estimator is a widely used technique for back-propagating gradients through discrete random variables.
RGB-D Individual Segmentation
Fine-grained recognition task deals with sub-category classification problem, which is important for real-world applications.
Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers
Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers.
Neural Network Model Extraction Attacks in Edge Devices by Hearing Architectural Hints
As neural networks continue their reach into nearly every aspect of software operations, the details of those networks become an increasingly sensitive subject.
Cryptography and Security Hardware Architecture
Recreation of the Periodic Table with an Unsupervised Machine Learning Algorithm
In 1869, the first draft of the periodic table was published by Russian chemist Dmitri Mendeleev.
DWM: A Decomposable Winograd Method for Convolution Acceleration
In this paper, we propose a novel Decomposable Winograd Method (DWM), which breaks through the limitation of original Winograd's minimal filtering algorithm to a wide and general convolutions.
Mixed Reinforcement Learning with Additive Stochastic Uncertainty
This paper presents a mixed reinforcement learning (mixed RL) algorithm by simultaneously using dual representations of environmental dynamics to search the optimal policy with the purpose of improving both learning accuracy and training speed.
Variational Policy Propagation for Multi-agent Reinforcement Learning
We propose a \emph{collaborative} multi-agent reinforcement learning algorithm named variational policy propagation (VPP) to learn a \emph{joint} policy through the interactions over agents.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
E-RNN: Design Optimization for Efficient Recurrent Neural Networks in FPGAs
It is a challenging task to have real-time, efficient, and accurate hardware RNN implementations because of the high sensitivity to imprecision accumulation and the requirement of special activation function implementations.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
HyperSTAR: Task-Aware Hyperparameters for Deep Networks
To reduce HPO time, we present HyperSTAR (System for Task Aware Hyperparameter Recommendation), a task-aware method to warm-start HPO for deep neural networks.
Towards Fine-grained Human Pose Transfer with Detail Replenishing Network
Human pose transfer (HPT) is an emerging research topic with huge potential in fashion design, media production, online advertising and virtual reality.
Inferring Vector Magnetic Fields from Stokes Profiles of GST/NIRIS Using a Convolutional Neural Network
By learning the latent patterns in the training data prepared by the physics-based ME tool, the proposed CNN method is able to infer vector magnetic fields from the Stokes profiles of GST/NIRIS.
Solar and Stellar Astrophysics
LRNNet: A Light-Weighted Network with Efficient Reduced Non-Local Operation for Real-Time Semantic Segmentation
Many of these applications need to perform a real-time and efficient prediction for semantic segmentation with a light-weighted network.
Machine Learning in Heliophysics and Space Weather Forecasting: A White Paper of Findings and Recommendations
The authors of this white paper met on 16-17 January 2020 at the New Jersey Institute of Technology, Newark, NJ, for a 2-day workshop that brought together a group of heliophysicists, data providers, expert modelers, and computer/data scientists.
Modeling Lost Information in Lossy Image Compression
Specifically, ILC introduces an invertible encoding module to replace the encoder-decoder structure to produce the low dimensional informative latent representation, meanwhile, transform the lost information into an auxiliary latent variable that won't be further coded or stored.
Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attacks
This paper investigates capabilities of Privacy-Preserving Deep Learning (PPDL) mechanisms against various forms of privacy attacks.
Variance Reduction and Quasi-Newton for Particle-Based Variational Inference
Particle-based Variational Inference methods (ParVIs), like Stein Variational Gradient Descent, are nonparametric variational inference methods that optimize a set of particles to best approximate a target distribution.
Attribute-conditioned Layout GAN for Automatic Graphic Design
In this paper, we introduce Attribute-conditioned Layout GAN to incorporate the attributes of design elements for graphic layout generation by forcing both the generator and the discriminator to meet attribute conditions.
GeneraLight: Improving Environment Generalization of Traffic Signal Control via Meta Reinforcement Learning
The heavy traffic congestion problem has always been a concern for modern cities.
Neighbor Class Consistency on Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) is to make predictions for unlabeled data in a target domain with labeled data from source domain available.
Latent Causal Invariant Model
To avoid spurious correlation, we propose a Latent Causal Invariance Model (LaCIM) which pursues causal prediction.
Computational Design and Fabrication of Corrugated Mechanisms from Behavioral Specifications
Based on an equivalent plate model, we develop and validate analytical formulas for the behavioral specifications of OADLC mechanisms; the analytical formulas can be described as expressions of design parameters.
Robotics
Towards Spatio-Temporal Video Scene Text Detection via Temporal Clustering
With only bounding-box annotations in the spatial domain, existing video scene text detection (VSTD) benchmarks lack temporal relation of text instances among video frames, which hinders the development of video text-related applications.
Strain-Rate-Dependent Deformation Behavior of Ti29Zr24Nb23Hf24 High Entropy Alloys at Elevated and Room Temperature
Such a softening behavior can be related to the interaction of dislocations with short-range clustering.
Materials Science
Deep Transfer Learning for Signal Detection in Ambient Backscatter Communications
To eliminate the requirement of channel estimation and to improve the system performance, in this paper, we adopt a deep transfer learning (DTL) approach to implicitly extract the features of channel and directly recover tag symbols.
Location-aware Predictive Beamforming for UAV Communications: A Deep Learning Approach
Unmanned aerial vehicle (UAV)-assisted communication becomes a promising technique to realize the beyond fifth generation (5G) wireless networks, due to the high mobility and maneuverability of UAVs which can adapt to heterogeneous requirements of different applications.
Deep Transfer Learning-Assisted Signal Detection for Ambient Backscatter Communications
Existing tag signal detection algorithms inevitably suffer from a high bit error rate (BER) due to the difficulties in estimating the channel state information (CSI).
Robustness Investigation on Deep Learning CT Reconstruction for Real-Time Dose Optimization
For organ-specific AEC, a preliminary CT reconstruction is necessary to estimate organ shapes for dose optimization, where only a few projections are allowed for real-time reconstruction.
Shed Various Lights on a Low-Light Image: Multi-Level Enhancement Guided by Arbitrary References
This paper proposes a neural network for multi-level low-light image enhancement, which is user-friendly to meet various requirements by selecting different images as brightness reference.
Non-equilibrium Flux Rope Formation by Confined Flares Preceding a Solar Coronal Mass Ejection
We present evidence that a magnetic flux rope was formed before a coronal mass ejection (CME) and its associated long-duration flare during a pair of preceding confined eruptions and associated impulsive flares in a compound event in NOAA Active Region 12371.
Solar and Stellar Astrophysics
Bridge the Vision Gap from Field to Command: A Deep Learning Network Enhancing Illumination and Details
With the goal of tuning up the brightness, low-light image enhancement enjoys numerous applications, such as surveillance, remote sensing and computational photography.
Towards Enhancing Fine-grained Details for Image Matting
In this paper, we argue that recovering these microscopic details relies on low-level but high-definition texture features.
Non-invasive Self-attention for Side Information Fusion in Sequential Recommendation
It is still an open question to leverage various types of information under the BERT framework.
Learning Invariant Representations across Domains and Tasks
Being expensive and time-consuming to collect massive COVID-19 image samples to train deep classification models, transfer learning is a promising approach by transferring knowledge from the abundant typical pneumonia datasets for COVID-19 image classification.
LSTMs and Deep Residual Networks for Carbohydrate and Bolus Recommendations in Type 1 Diabetes Management
In this work, we invert the "what-if" scenario and introduce a similar architecture based on chaining two LSTMs that can be trained to make either insulin or carbohydrate recommendations aimed at reaching a desired BG level in the future.
Ternary Hashing
This paper proposes a novel ternary hash encoding for learning to hash methods, which provides a principled more efficient coding scheme with performances better than those of the state-of-the-art binary hashing counterparts.
Dialogue History Matters! Personalized Response Selectionin Multi-turn Retrieval-based Chatbots
To fill the gap between these up-to-date methods and the real-world applications, we incorporate user-specific dialogue history into the response selection and propose a personalized hybrid matching network (PHMN).
Learning to Simulate on Sparse Trajectory Data
Simulation of the real-world traffic can be used to help validate the transportation policies.
AET-EFN: A Versatile Design for Static and Dynamic Event-Based Vision
The neuromorphic event cameras, which capture the optical changes of a scene, have drawn increasing attention due to their high speed and low power consumption.
CSTNet: A Dual-Branch Convolutional Network for Imaging of Reactive Flows using Chemical Species Tomography
Chemical Species Tomography (CST) has been widely used for in situ imaging of critical parameters, e. g. species concentration and temperature, in reactive flows.
Learnable Expansion-and-Compression Network for Few-shot Class-Incremental Learning
By tentatively expanding network nodes, LEC-Net enlarges the representation capacity of features, alleviating feature drift of old network from the perspective of model regularization.
Reconstruction Condition of Quantized Signals in Unlimited Sampling Framework
The latest theoretical advances in the field of unlimited sampling framework (USF) show the potential to avoid clipping problems of analog-to-digital converters (ADC).
Cost-Effective Quasi-Parallel Sensing Instrumentation for Industrial Chemical Species Tomography
Although a fully parallel data acquisition (DAQ) and signal processing system can achieve these functionalities with maximised temporal response, it leads to a highly complex, expensive and power-consuming instrumentation system with high potential for inconsistency between the sampled beams due to the electronics alone.
Spatio-Temporal Hierarchical Adaptive Dispatching for Ridesharing Systems
Thus, in this paper, we exploit adaptive dispatching intervals to boost the platform's profit under a guarantee of the maximum passenger waiting time.
Underwater Target Recognition based on Multi-Decision LOFAR Spectrum Enhancement: A Deep Learning Approach
To overcome this issue and to further improve the recognition performance, we adopt a deep learning approach for underwater target recognition and propose a LOFAR spectrum enhancement (LSE)-based underwater target recognition scheme, which consists of preprocessing, offline training, and online testing.
Learning to Route via Theory-Guided Residual Network
Therefore, in this paper, we propose to learn the human routing model, which is one of the most essential part in the traffic simulator.
Target-Dependent Chemical Species Tomography with Hybrid Meshing of Sensing Regions
The proposed scheme was both numerically and experimentally validated using a CST sensor with 32 laser beams using a variety of computational tomographic algorithms.
Hierarchical Temperature Imaging Using Pseudo-Inversed Convolutional Neural Network Aided TDLAS Tomography
As an in situ combustion diagnostic tool, Tunable Diode Laser Absorption Spectroscopy (TDLAS) tomography has been widely used for imaging of two-dimensional temperature distributions in reactive flows.
BLCU-NLP at SemEval-2020 Task 5: Data Augmentation for Efficient Counterfactual Detecting
We demonstrate the effectiveness of our approaches, which achieves 0. 95 of subtask 1 in F1 while using only a subset of giving training set to fine-tune the BERT model, and our official submission achieves F1 0. 802, which ranks us 16th in the competition.
Light Pollution Reduction in Nighttime Photography
Nighttime photographers are often troubled by light pollution of unwanted artificial lights.
Pre-training transformer-based framework on large-scale pediatric claims data for downstream population-specific tasks
In addition, our framework showed a great generalizability potential to transfer learned knowledge from one institution to another, paving the way for future healthcare model pre-training across institutions.
Transformer-based unsupervised patient representation learning based on medical claims for risk stratification and analysis
The claims data, containing medical codes, services information, and incurred expenditure, can be a good resource for estimating an individual's health condition and medical risk level.
A mechanistic-based data-driven approach to accelerate structural topology optimization through finite element convolutional neural network (FE-CNN)
During offline training, a mapping function is built between high and low resolution representations of a given design domain.
