Search Results for author:
Found 159 papers, 79 papers with code
Improved Word Sense Disambiguation with Enhanced Sense Representations
Current state-of-the-art supervised word sense disambiguation (WSD) systems (such as GlossBERT and bi-encoder model) yield surprisingly good results by purely leveraging pre-trained language models and short dictionary definitions (or glosses) of the different word senses.
Ranked #2 on
Word Sense Disambiguation
on Supervised:
E-ConvRec: A Large-Scale Conversational Recommendation Dataset for E-Commerce Customer Service
There has been a growing interest in developing conversational recommendation system (CRS), which provides valuable recommendations to users through conversations.
Generative Retrieval with Semantic Tree-Structured Item Identifiers via Contrastive Learning
To obtain efficiency and effectiveness, this paper introduces a generative retrieval framework, namely SEATER, which learns SEmAntic Tree-structured item identifiERs via contrastive learning.
Speech-Gesture GAN: Gesture Generation for Robots and Embodied Agents
In order to train our neural network model, we employ a public dataset containing co-speech gestures with corresponding speech audio utterances, which were captured from a single male native English speaker.
Learning and Optimization of Implicit Negative Feedback for Industrial Short-video Recommender System
Short-video recommendation is one of the most important recommendation applications in today's industrial information systems.
Generalizable Zero-Shot Speaker Adaptive Speech Synthesis with Disentangled Representations
However, most current approaches suffer from the degradation of naturalness and speaker similarity when synthesizing speech for unseen speakers (i. e., speakers not in the training dataset) due to the poor generalizability of the model in out-of-distribution data.
SHARK: A Lightweight Model Compression Approach for Large-scale Recommender Systems
Increasing the size of embedding layers has shown to be effective in improving the performance of recommendation models, yet gradually causing their sizes to exceed terabytes in industrial recommender systems, and hence the increase of computing and storage costs.
Understanding and Modeling Passive-Negative Feedback for Short-video Sequential Recommendation
To enhance the robustness of our model, we then introduce a multi-task learning module to simultaneously optimize two kinds of feedback -- passive-negative feedback and traditional randomly-sampled negative feedback.
Graph Contrastive Learning with Generative Adversarial Network
Specifically, we present GACN, a novel Generative Adversarial Contrastive learning Network for graph representation learning.
Enhancing Job Recommendation through LLM-based Generative Adversarial Networks
However, directly leveraging LLMs to enhance recommendation results is not a one-size-fits-all solution, as LLMs may suffer from fabricated generation and few-shot problems, which degrade the quality of resume completion.
TractGeoNet: A geometric deep learning framework for pointwise analysis of tract microstructure to predict language assessment performance
We evaluate the effectiveness of the proposed method by predicting individual performance on two neuropsychological assessments of language using a dataset of 20 association white matter fiber tracts from 806 subjects from the Human Connectome Project.
SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generation
Diffusion models based on permutation-equivariant networks can learn permutation-invariant distributions for graph data.
Leveraging Watch-time Feedback for Short-Video Recommendations: A Causal Labeling Framework
With the proliferation of short video applications, the significance of short video recommendations has vastly increased.
Reciprocal Sequential Recommendation
Existing RRS models mainly capture static user preferences, which have neglected the evolving user tastes and the dynamic matching relation between the two parties.
KuaiSAR: A Unified Search And Recommendation Dataset
We believe this dataset will serve as a catalyst for innovative research and bridge the gap between academia and industry in understanding the S&R services in practical, real-world applications.
PANE-GNN: Unifying Positive and Negative Edges in Graph Neural Networks for Recommendation
Recommender systems play a crucial role in addressing the issue of information overload by delivering personalized recommendations to users.
Node Embedding from Neural Hamiltonian Orbits in Graph Neural Networks
In the graph node embedding problem, embedding spaces can vary significantly for different data types, leading to the need for different GNN model types.
Graph Neural Convection-Diffusion with Heterophily
Graph neural networks (GNNs) have shown promising results across various graph learning tasks, but they often assume homophily, which can result in poor performance on heterophilic graphs.
Instant Representation Learning for Recommendation over Large Dynamic Graphs
Furthermore, the Neighborhood Disturbance existing in dynamic graphs deteriorates the performance of neighbor-aggregation based graph models.
Multi-behavior Self-supervised Learning for Recommendation
Secondly, existing methods utilizing self-supervised learning (SSL) to tackle the data sparsity neglect the serious optimization imbalance between the SSL task and the target task.
When Search Meets Recommendation: Learning Disentangled Search Representation for Recommendation
In our paper, we propose a Search-Enhanced framework for the Sequential Recommendation (SESRec) that leverages users' search interests for recommendation, by disentangling similar and dissimilar representations within S&R behaviors.
HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion
LiDAR relocalization plays a crucial role in many fields, including robotics, autonomous driving, and computer vision.
Hybrid Dual Mean-Teacher Network With Double-Uncertainty Guidance for Semi-Supervised Segmentation of MRI Scans
We then propose a hybrid regularization module to encourage both student models to produce results close to the uncertainty-weighted hybrid prediction.
Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition
In this work, we propose to automatically design efficient 3D CNN architectures via a novel training-free neural architecture search approach tailored for 3D CNNs considering the model complexity.
Ranked #73 on
Action Recognition
on Something-Something V2
Consistency Models
Through extensive experiments, we demonstrate that they outperform existing distillation techniques for diffusion models in one- and few-step sampling, achieving the new state-of-the-art FID of 3. 55 on CIFAR-10 and 6. 20 on ImageNet 64x64 for one-step generation.
Ranked #7 on
Image Generation
on ImageNet 64x64
Node Embedding from Hamiltonian Information Propagation in Graph Neural Networks
Graph neural networks (GNNs) have achieved success in various inference tasks on graph-structured data.
Multimodal Trajectory Prediction: A Survey
Trajectory prediction is an important task to support safe and intelligent behaviours in autonomous systems.
Dual-interest Factorization-heads Attention for Sequential Recommendation
In this paper, we propose Dual-interest Factorization-heads Attention for Sequential Recommendation (short for DFAR) consisting of feedback-aware encoding layer, dual-interest disentangling layer and prediction layer.
TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou
And for the user-item cross features, we compress each into a one-dimentional bias term in the attention score calculation to save the computational cost.
PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Information
By infusing personalized selection of Embedding and personalized modification of DNN parameters, PEPNet tailored to the interests of each individual obtains significant performance gains, with online improvements exceeding 1\% in multiple task metrics across multiple domains.
TractGraphCNN: anatomically informed graph CNN for classification using diffusion MRI tractography
This work shows the potential of incorporating anatomical information, especially known anatomical similarities between input features, to guide convolutions in neural networks.
EZInterviewer: To Improve Job Interview Performance with Mock Interview Generator
The key idea is to reduce the number of parameters that rely on interview dialogs by disentangling the knowledge selector and dialog generator so that most parameters can be trained with ungrounded dialogs as well as the resume data that are not low-resource.
1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results
The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection.
Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training
Generating images from graph-structured inputs, such as scene graphs, is uniquely challenging due to the difficulty of aligning nodes and connections in graphs with objects and their relations in images.
Uncertainty Sentence Sampling by Virtual Adversarial Perturbation
Active learning for sentence understanding attempts to reduce the annotation cost by identifying the most informative examples.
AutoLV: Automatic Lecture Video Generator
We propose an end-to-end lecture video generation system that can generate realistic and complete lecture videos directly from annotated slides, instructor's reference voice and instructor's reference portrait video.
On the Robustness of Graph Neural Diffusion to Topology Perturbations
In this work, we explore the robustness properties of graph neural PDEs.
Diffusion Models: A Comprehensive Survey of Methods and Applications
This survey aims to provide a contextualized, in-depth look at the state of diffusion models, identifying the key areas of focus and pointing to potential areas for further exploration.
Billion-user Customer Lifetime Value Prediction: An Industrial-scale Solution from Kuaishou
Customer Life Time Value (LTV) is the expected total revenue that a single user can bring to a business.
Modeling Two-Way Selection Preference for Person-Job Fit
To model the two-way selection preference from the dual-perspective of job seekers and employers, we incorporate two different nodes for each candidate (or job) and characterize both successful matching and failed matching via a unified dual-perspective interaction graph.
HybridGNN: Learning Hybrid Representation in Multiplex Heterogeneous Networks
One of the most important tasks in recommender systems is to predict the potential connection between two nodes under a specific edge type (i. e., relationship).
Superficial White Matter Analysis: An Efficient Point-cloud-based Deep Learning Framework with Supervised Contrastive Learning for Consistent Tractography Parcellation across Populations and dMRI Acquisitions
We propose a novel two-stage deep-learning-based framework, Superficial White Matter Analysis (SupWMA), that performs an efficient and consistent parcellation of 198 SWM clusters from whole-brain tractography.
White Matter Tracts are Point Clouds: Neuropsychological Score Prediction and Critical Region Localization via Geometric Deep Learning
In this paper, we propose a deep-learning-based framework for neuropsychological score prediction using microstructure measurements estimated from diffusion magnetic resonance imaging (dMRI) tractography, focusing on predicting performance on a receptive vocabulary assessment task based on a critical fiber tract for language, the arcuate fasciculus (AF).
Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Prediction
Pedestrian trajectory prediction is an essential and challenging task for a variety of real-life applications such as autonomous driving and robotic motion planning.
When Multi-Level Meets Multi-Interest: A Multi-Grained Neural Model for Sequential Recommendation
Specifically, multi-interest methods such as ComiRec and MIMN, focus on extracting different interests for a user by performing historical item clustering, while graph convolution methods including TGSRec and SURGE elect to refine user preferences based on multi-level correlations between historical items.
Deep fiber clustering: Anatomically informed fiber clustering with self-supervised deep learning for fast and effective tractography parcellation
In this work, we propose a novel deep learning framework for white matter fiber clustering, Deep Fiber Clustering (DFC), which solves the unsupervised clustering problem as a self-supervised learning task with a domain-specific pretext task to predict pairwise fiber distances.
Computer-Aided Extraction of Select MRI Markers of Cerebral Small Vessel Disease: A Systematic Review
Cerebral small vessel disease (CSVD) is a major vascular contributor to cognitive impairment in ageing, including dementias.
Leveraging Search History for Improving Person-Job Fit
As the core technique of online recruitment platforms, person-job fit can improve hiring efficiency by accurately matching job positions with qualified candidates.
Explainability in Graph Neural Networks: An Experimental Survey
Graph neural networks (GNNs) have been extensively developed for graph representation learning in various application domains.
Towards Bi-directional Skip Connections in Encoder-Decoder Architectures and Beyond
With the backward skip connections, we propose a U-Net based network family, namely Bi-directional O-shape networks, which set new benchmarks on multiple public medical imaging segmentation datasets.
GrainSpace: A Large-scale Dataset for Fine-grained and Domain-adaptive Recognition of Cereal Grains
To the best of our knowledge, GrainSpace is the first publicly released dataset for cereal grain inspection.
GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation
GeoDiff treats each atom as a particle and learns to directly reverse the diffusion process (i. e., transforming from a noise distribution to stable conformations) as a Markov chain.
StrongSORT: Make DeepSORT Great Again
As a result, the construction of a good baseline for a fair comparison is essential.
Ranked #5 on
Multi-Object Tracking
on MOT17
(using extra training data)
Disentangling Long and Short-Term Interests for Recommendation
Modeling user's long-term and short-term interests is crucial for accurate recommendation.
A Model-Agnostic Causal Learning Framework for Recommendation using Search Data
In this paper, we propose a model-agnostic framework named IV4Rec that can effectively decompose the embedding vectors into these two parts, hence enhancing recommendation results.
SupWMA: Consistent and Efficient Tractography Parcellation of Superficial White Matter with Deep Learning
Most parcellation methods focus on the deep white matter (DWM), while fewer methods address the superficial white matter (SWM) due to its complexity.
A Wearable ECG Monitor for Deep Learning Based Real-Time Cardiovascular Disease Detection
Cardiovascular disease has become one of the most significant threats endangering human life and health.
Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement
Recent advances in unsupervised domain adaptation (UDA) techniques have witnessed great success in cross-domain computer vision tasks, enhancing the generalization ability of data-driven deep learning architectures by bridging the domain distribution gaps.
Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving
3D human pose estimation (HPE) in autonomous vehicles (AV) differs from other use cases in many factors, including the 3D resolution and range of data, absence of dense depth maps, failure modes for LiDAR, relative location between the camera and LiDAR, and a high bar for estimation accuracy.
3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysis
General point clouds have been increasingly investigated for different tasks, and recently Transformer-based networks are proposed for point cloud analysis.
Ranked #1 on
3D Point Cloud Classification
on IntrA
Density Ratio Estimation via Infinitesimal Classification
We then estimate the instantaneous rate of change of the bridge distributions indexed by time (the "time score") -- a quantity defined analogously to data (Stein) scores -- with a novel time score matching objective.
Solving Inverse Problems in Medical Imaging with Score-Based Generative Models
These measurements are typically synthesized from images using a fixed physical model of the measurement process, which hinders the generalization capability of models to unknown measurement processes.
Estimating High Order Gradients of the Data Distribution by Denoising
By leveraging Tweedie's formula on higher order moments, we generalize denoising score matching to estimate higher order derivatives.
Pseudo-Spherical Contrastive Divergence
Energy-based models (EBMs) offer flexible distribution parametrization.
Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks
By ensuring that the equilibrium points of the ODE solution used as part of SODEF is Lyapunov-stable, the ODE solution for an input with a small perturbation converges to the same solution as the unperturbed input.
Score-Based Generative Classifiers
In this work, we investigate score-based generative models as classifiers for natural images.
Concept-Aware Denoising Graph Neural Network for Micro-Video Recommendation
In this paper, we propose a novel concept-aware denoising graph neural network (named CONDE) for micro-video recommendation.
DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysis
With image-level labels only, patch-wise classification would be sub-optimal due to inconsistency between the patch appearance and image-level label.
Voxel-wise Cross-Volume Representation Learning for 3D Neuron Reconstruction
Recently, a series of deep learning based segmentation methods have been proposed to improve the quality of raw 3D optical image stacks by removing noises and restoring neuronal structures from low-contrast background.
Discriminative Latent Semantic Graph for Video Captioning
Video captioning aims to automatically generate natural language sentences that can describe the visual contents of a given video.
SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations
The key challenge is balancing faithfulness to the user input (e. g., hand-drawn colored strokes) and realism of the synthesized image.
Deep Fiber Clustering: Anatomically Informed Unsupervised Deep Learning for Fast and Effective White Matter Parcellation
White matter fiber clustering (WMFC) enables parcellation of white matter tractography for applications such as disease classification and anatomical tract segmentation.
CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation
In this paper, we propose Conditional Score-based Diffusion models for Imputation (CSDI), a novel time series imputation method that utilizes score-based diffusion models conditioned on observed data.
PhotoChat: A Human-Human Dialogue Dataset with Photo Sharing Behavior for Joint Image-Text Modeling
Based on this dataset, we propose two tasks to facilitate research on image-text modeling: a photo-sharing intent prediction task that predicts whether one intends to share a photo in the next conversation turn, and a photo retrieval task that retrieves the most relevant photo according to the dialogue context.
Ranked #5 on
Image Retrieval
on PhotoChat
Sequential Recommendation with Graph Neural Networks
This helps explicitly distinguish users' core interests, by forming dense clusters in the interest graph.
BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation
We evaluate BiX-NAS on two segmentation tasks using three different medical image datasets, and the experimental results show that our BiX-NAS searched architecture achieves the state-of-the-art performance with significantly lower computational cost.
Partial Graph Reasoning for Neural Network Regularization
This add-on graph regularizes the network during training and can be completely skipped during inference.
Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis
Discrete point cloud objects lack sufficient shape descriptors of 3D geometries.
Ranked #10 on
3D Part Segmentation
on ShapeNet-Part
Multiple Sclerosis Lesion Analysis in Brain Magnetic Resonance Images: Techniques and Clinical Applications
Further, we review technical strategies, such as domain adaptation, to enhance MS lesion segmentation in real-world clinical settings.
Improved Autoregressive Modeling with Distribution Smoothing
While autoregressive models excel at image compression, their sample quality is often lacking.
Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis
Scene understanding is a critical problem in computer vision.
Ranked #4 on
3d scene graph generation
on 3DSSG
Anytime Sampling for Autoregressive Models via Ordered Autoencoding
Experimentally, we demonstrate in several image and audio generation tasks that sample quality degrades gracefully as we reduce the computational budget for sampling.
CellTrack R-CNN: A Novel End-To-End Deep Neural Network for Cell Segmentation and Tracking in Microscopy Images
Cell segmentation and tracking in microscopy images are of great significance to new discoveries in biology and medicine.
Maximum Likelihood Training of Score-Based Diffusion Models
Score-based diffusion models synthesize samples by reversing a stochastic process that diffuses data to noise, and are trained by minimizing a weighted combination of score matching losses.
Ranked #5 on
Image Generation
on ImageNet 32x32
(bpd metric)
Single Neuron Segmentation using Graph-based Global Reasoning with Auxiliary Skeleton Loss from 3D Optical Microscope Images
One of the critical steps in improving accurate single neuron reconstruction from three-dimensional (3D) optical microscope images is the neuronal structure segmentation.
How to Train Your Energy-Based Models
Energy-Based Models (EBMs), also known as non-normalized probabilistic models, specify probability density or mass functions up to an unknown normalizing constant.
Understanding Classifiers with Generative Models
Although deep neural networks are effective on supervised learning tasks, they have been shown to be brittle.
Fast WordPiece Tokenization
For general text, we further propose an algorithm that combines pre-tokenization (splitting the text into words) and our linear-time WordPiece method into a single pass.
Learning Energy-Based Models by Diffusion Recovery Likelihood
Inspired by recent progress on diffusion probabilistic models, we present a diffusion recovery likelihood method to tractably learn and sample from a sequence of EBMs trained on increasingly noisy versions of a dataset.
Ranked #15 on
Image Generation
on CelebA 64x64
Score-Based Generative Modeling through Stochastic Differential Equations
Combined with multiple architectural improvements, we achieve record-breaking performance for unconditional image generation on CIFAR-10 with an Inception score of 9. 89 and FID of 2. 20, a competitive likelihood of 2. 99 bits/dim, and demonstrate high fidelity generation of 1024 x 1024 images for the first time from a score-based generative model.
Ranked #14 on
Image Generation
on CIFAR-10
Autoregressive Score Matching
To increase flexibility, we propose autoregressive conditional score models (AR-CSM) where we parameterize the joint distribution in terms of the derivatives of univariate log-conditionals (scores), which need not be normalized.
Imitation with Neural Density Models
We propose a new framework for Imitation Learning (IL) via density estimation of the expert's occupancy measure followed by Maximum Occupancy Entropy Reinforcement Learning (RL) using the density as a reward.
Understanding Classifier Mistakes with Generative Models
From this observation, we develop a detection criteria for samples on which a classifier is likely to fail at test time.
Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network
Compared with pure text-based matching models, the proposed approach is able to learn better data representations from limited or even sparse interaction data, which is more resistible to noise in training data.
PDAM: A Panoptic-Level Feature Alignment Framework for Unsupervised Domain Adaptive Instance Segmentation in Microscopy Images
In this work, we present an unsupervised domain adaptation (UDA) method, named Panoptic Domain Adaptive Mask R-CNN (PDAM), for unsupervised instance segmentation in microscopy images.
Efficient Learning of Generative Models via Finite-Difference Score Matching
Several machine learning applications involve the optimization of higher-order derivatives (e. g., gradients of gradients) during training, which can be expensive in respect to memory and computation even with automatic differentiation.
BiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder Architecture
U-Net has become one of the state-of-the-art deep learning-based approaches for modern computer vision tasks such as semantic segmentation, super resolution, image denoising, and inpainting.
Improved Techniques for Training Score-Based Generative Models
Score-based generative models can produce high quality image samples comparable to GANs, without requiring adversarial optimization.
Ranked #82 on
Image Generation
on CIFAR-10
Detecting Problem Statements in Peer Assessments
We attempt to automate the process of deciding whether a review comment detects a problem.
Gleason Score Prediction using Deep Learning in Tissue Microarray Image
Prostate cancer (PCa) is one of the most common cancers in men around the world.
ICE-GAN: Identity-aware and Capsule-Enhanced GAN with Graph-based Reasoning for Micro-Expression Recognition and Synthesis
Micro-expressions are reflections of people's true feelings and motives, which attract an increasing number of researchers into the study of automatic facial micro-expression recognition.
Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re-weighting
More specifically, we first propose a nuclei inpainting mechanism to remove the auxiliary generated objects in the synthesized images.
Shape-Oriented Convolution Neural Network for Point Cloud Analysis
Point cloud is a principal data structure adopted for 3D geometric information encoding.
Improving 3D Object Detection through Progressive Population Based Augmentation
Data augmentation has been widely adopted for object detection in 3D point clouds.
Diversity can be Transferred: Output Diversification for White- and Black-box Attacks
Adversarial attacks often involve random perturbations of the inputs drawn from uniform or Gaussian distributions, e. g., to initialize optimization-based white-box attacks or generate update directions in black-box attacks.
Training Deep Energy-Based Models with f-Divergence Minimization
Experimental results demonstrate the superiority of f-EBM over contrastive divergence, as well as the benefits of training EBMs using f-divergences other than KL.
Gaussianization Flows
Iterative Gaussianization is a fixed-point iteration procedure that can transform any continuous random vector into a Gaussian one.
Permutation Invariant Graph Generation via Score-Based Generative Modeling
In particular, we design a permutation equivariant, multi-channel graph neural network to model the gradient of the data distribution at the input graph (a. k. a., the score function).
Panoptic Feature Fusion Net: A Novel Instance Segmentation Paradigm for Biomedical and Biological Images
Specifically, our proposed PFFNet contains a residual attention feature fusion mechanism to incorporate the instance prediction with the semantic features, in order to facilitate the semantic contextual information learning in the instance branch.
Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving
Feedforward computation, such as evaluating a neural network or sampling from an autoregressive model, is ubiquitous in machine learning.
Region and Object based Panoptic Image Synthesis through Conditional GANs
Our contribution consists of the proposal of a significant task worth investigating and a naive baseline of solving it.
Error-Correcting Output Codes with Ensemble Diversity for Robust Learning in Neural Networks
Though deep learning has been applied successfully in many scenarios, malicious inputs with human-imperceptible perturbations can make it vulnerable in real applications.
Domain Adaptation for Person-Job Fit with Transferable Deep Global Match Network
Furthermore, we extend the match network and implement domain adaptation in three levels, sentence-level representation, sentence-level match, and global match.
Unsupervised Out-of-Distribution Detection with Batch Normalization
Based on this insight, we propose to exploit in-batch dependencies for OoD detection.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Efficient Graph Generation with Graph Recurrent Attention Networks
Our model generates graphs one block of nodes and associated edges at a time.
Representation Learning with Ordered Relation Paths for Knowledge Graph Completion
Recently, a few methods take relation paths into consideration but pay less attention to the order of relations in paths which is important for reasoning.
Ranked #3 on
Link Prediction
on FB15k
(MR metric)
Towards Certified Defense for Unrestricted Adversarial Attacks
Our defense draws inspiration from differential privacy, and is based on intentionally adding noise to the classifier's outputs to limit the attacker's knowledge about the parameters.
Extremely Small BERT Models from Mixed-Vocabulary Training
Pretrained language models like BERT have achieved good results on NLP tasks, but are impractical on resource-limited devices due to memory footprint.
A General Data Renewal Model for Prediction Algorithms in Industrial Data Analytics
In industrial data analytics, one of the fundamental problems is to utilize the temporal correlation of the industrial data to make timely predictions in the production process, such as fault prediction and yield prediction.
Nuclei Segmentation via a Deep Panoptic Model with Semantic Feature Fusion
Automated detection and segmentation of individual nuclei in histopathology images is important for cancer diagnosis and prognosis.
LSTM-based Flow Prediction
In this paper, a method of prediction on continuous time series variables from the production or flow -- an LSTM algorithm based on multivariate tuning -- is proposed.
MintNet: Building Invertible Neural Networks with Masked Convolutions
To demonstrate their flexibility, we show that our invertible neural networks are competitive with ResNets on MNIST and CIFAR-10 classification.
Ranked #4 on
Image Generation
on MNIST
Generative Modeling by Estimating Gradients of the Data Distribution
We introduce a new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching.
Ranked #118 on
Image Generation
on CIFAR-10
Generating Long and Informative Reviews with Aspect-Aware Coarse-to-Fine Decoding
In this paper, we propose a novel review generation model by characterizing an elaborately designed aspect-aware coarse-to-fine generation process.
Geo-Aware Networks for Fine-Grained Recognition
By leveraging geolocation information we improve top-1 accuracy in iNaturalist from 70. 1% to 79. 0% for a strong baseline image-only model.
Sliced Score Matching: A Scalable Approach to Density and Score Estimation
However, it has been so far limited to simple, shallow models or low-dimensional data, due to the difficulty of computing the Hessian of log-density functions.
Class-Balanced Loss Based on Effective Number of Samples
We design a re-weighting scheme that uses the effective number of samples for each class to re-balance the loss, thereby yielding a class-balanced loss.
Ranked #2 on
Long-tail Learning
on EGTEA
Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning
Although the state-of-the-art attacking techniques that incorporated the advance of Generative adversarial networks (GANs) could construct class representatives of the global data distribution among all clients, it is still challenging to distinguishably attack a specific client (i. e., user-level privacy leakage), which is a stronger privacy threat to precisely recover the private data from a specific client.
Panoptic Segmentation with an End-to-End Cell R-CNN for Pathology Image Analysis
The morphological clues of various cancer cells are essential for pathologists to determine the stages of cancers.
Ranked #1 on
Nuclear Segmentation
on Cell17
Learning to Recommend with Multiple Cascading Behaviors
To fully exploit the signal in the data of multiple types of behaviors, we perform a joint optimization based on the multi-task learning framework, where the optimization on a behavior is treated as a task.
Deep Dual Pyramid Network for Barcode Segmentation using Barcode-30k Database
Specifically, a synthesizing method was proposed to generate well-annotated images containing barcode and QR code labels, which contributes to largely decrease the annotation time.
3D Global Convolutional Adversarial Network\\ for Prostate MR Volume Segmentation
In this paper, we propose a 3D Global Convolutional Adversarial Network (3D GCA-Net) to address efficient prostate MR volume segmentation.
Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning
We propose a measure to estimate domain similarity via Earth Mover's Distance and demonstrate that transfer learning benefits from pre-training on a source domain that is similar to the target domain by this measure.
Ranked #27 on
Fine-Grained Image Classification
on CUB-200-2011
Fine-Grained Image Classification
Fine-Grained Visual Categorization
+1
Constructing Unrestricted Adversarial Examples with Generative Models
Then, conditioned on a desired class, we search over the AC-GAN latent space to find images that are likely under the generative model and are misclassified by a target classifier.
Talking Face Generation by Conditional Recurrent Adversarial Network
Given an arbitrary face image and an arbitrary speech clip, the proposed work attempts to generating the talking face video with accurate lip synchronization while maintaining smooth transition of both lip and facial movement over the entire video clip.
Accelerating Natural Gradient with Higher-Order Invariance
An appealing property of the natural gradient is that it is invariant to arbitrary differentiable reparameterizations of the model.
Decoupled Learning for Conditional Adversarial Networks
Incorporating encoding-decoding nets with adversarial nets has been widely adopted in image generation tasks.
PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
Adversarial perturbations of normal images are usually imperceptible to humans, but they can seriously confuse state-of-the-art machine learning models.
Locally-Transferred Fisher Vectors for Texture Classification
Texture classification has been extensively studied in computer vision.
Person Re-identification Using Visual Attention
Despite recent attempts for solving the person re-identification problem, it remains a challenging task since a person's appearance can vary significantly when large variations in view angle, human pose, and illumination are involved.
The iNaturalist Species Classification and Detection Dataset
Existing image classification datasets used in computer vision tend to have a uniform distribution of images across object categories.
Ranked #8 on
Image Classification
on iNaturalist
Learning Unified Embedding for Apparel Recognition
To ease the training difficulty, a novel learning scheme is proposed by using the output from specialized models as learning targets so that L2 loss can be used instead of triplet loss.
r-BTN: Cross-domain Face Composite and Synthesis from Limited Facial Patches
A more generalized question is that if a large proportion (e. g., more than 50%) of the face/sketch is missing, can a realistic whole face sketch/image still be estimated.
Age Progression/Regression by Conditional Adversarial Autoencoder
In CAAE, the face is first mapped to a latent vector through a convolutional encoder, and then the vector is projected to the face manifold conditional on age through a deconvolutional generator.
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.
Speed/accuracy trade-offs for modern convolutional object detectors
On the opposite end in which accuracy is critical, we present a detector that achieves state-of-the-art performance measured on the COCO detection task.
Ranked #224 on
Object Detection
on COCO test-dev
Derivative Delay Embedding: Online Modeling of Streaming Time Series
The staggering amount of streaming time series coming from the real world calls for more efficient and effective online modeling solution.
Kernel Bayesian Inference with Posterior Regularization
We propose a vector-valued regression problem whose solution is equivalent to the reproducing kernel Hilbert space (RKHS) embedding of the Bayesian posterior distribution.
Improving the Robustness of Deep Neural Networks via Stability Training
In this paper we address the issue of output instability of deep neural networks: small perturbations in the visual input can significantly distort the feature embeddings and output of a neural network.
Bayesian Matrix Completion via Adaptive Relaxed Spectral Regularization
Bayesian matrix completion has been studied based on a low-rank matrix factorization formulation with promising results.
Training Deep Neural Networks via Direct Loss Minimization
Supervised training of deep neural nets typically relies on minimizing cross-entropy.
Fusing Subcategory Probabilities for Texture Classification
Texture, as a fundamental characteristic of objects, has attracted much attention in computer vision research.
Learning Semantic Relationships for Better Action Retrieval in Images
Human actions capture a wide variety of interactions between people and objects.
A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems
We extend the model to jointly learn from features of items from different domains and user features by introducing a multi-view Deep Learning model.
An Overview of Microsoft Academic Service (MAS) and Applications
In addition to obtaining these entities from the publisher feeds as in the previous effort, we in this version include data mining results from the Web index and an in-house knowledge base from Bing, a major commercial search engine.
Learning Fine-grained Image Similarity with Deep Ranking
This paper proposes a deep ranking model that employs deep learning techniques to learn similarity metric directly from images. It has higher learning capability than models based on hand-crafted features.