Search Results for author:
Found 111 papers, 37 papers with code
A Neural RDE-based model for solving path-dependent PDEs
The concept of the path-dependent partial differential equation (PPDE) was first introduced in the context of path-dependent derivatives in financial markets.
SPRING: GPT-4 Out-performs RL Algorithms by Studying Papers and Reasoning
Finally, we show the potential of games as a test bed for LLMs.
NODE-ImgNet: a PDE-informed effective and robust model for image denoising
Inspired by the traditional partial differential equation (PDE) approach for image denoising, we propose a novel neural network architecture, referred as NODE-ImgNet, that combines neural ordinary differential equations (NODEs) with convolutional neural network (CNN) blocks.
Multi-spectral Class Center Network for Face Manipulation Detection and Localization
Next, a novel Multi-Spectral Class Center Network (MSCCNet) is proposed for face manipulation detection and localization.
Uniform-PAC Guarantees for Model-Based RL with Bounded Eluder Dimension
Recently, there has been remarkable progress in reinforcement learning (RL) with general function approximation.
Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents
We propose the Plan, Eliminate, and Track (PET) framework.
Personalized Federated Learning under Mixture of Distributions
The recent trend towards Personalized Federated Learning (PFL) has garnered significant attention as it allows for the training of models that are tailored to each client while maintaining data privacy.
Score-based Transport Modeling for Mean-Field Fokker-Planck Equations
We use the score-based transport modeling method to solve the mean-field Fokker-Planck equations, which we call MSBTM.
Elastic Interaction Energy-Based Generative Model: Approximation in Feature Space
We adopt the GAN framework and replace the discriminator with a feature transformation network to map the data into a latent space.
Borda Regret Minimization for Generalized Linear Dueling Bandits
Surprisingly, the Borda regret minimization problem turns out to be difficult, as we prove a regret lower bound of order $\Omega(d^{2/3} T^{2/3})$, where $d$ is the dimension of contextual vectors and $T$ is the time horizon.
Video Waterdrop Removal via Spatio-Temporal Fusion in Driving Scenes
The waterdrops on windshields during driving can cause severe visual obstructions, which may lead to car accidents.
Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals
Read and Reward speeds up RL algorithms on Atari games by reading manuals released by the Atari game developers.
Avoiding spurious correlations via logit correction
Empirical studies suggest that machine learning models trained with empirical risk minimization (ERM) often rely on attributes that may be spuriously correlated with the class labels.
How to Describe Images in a More Funny Way? Towards a Modular Approach to Cross-Modal Sarcasm Generation
Sarcasm generation has been investigated in previous studies by considering it as a text-to-text generation problem, i. e., generating a sarcastic sentence for an input sentence.
Bayesian Layer Graph Convolutioanl Network for Hyperspetral Image Classification
In recent years, research on hyperspectral image (HSI) classification has continuous progress on introducing deep network models, and recently the graph convolutional network (GCN) based models have shown impressive performance.
Sybil-Proof Diffusion Auction in Social Networks
A diffusion auction is a market to sell commodities over a social network, where the challenge is to incentivize existing buyers to invite their neighbors in the network to join the market.
AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatars
To achieve meaningful control over facial expressions via deformation, we propose a 3D-level imitative learning scheme between the generator and a parametric 3D face model during adversarial training of the 3D-aware GAN.
Towards Consistency and Complementarity: A Multiview Graph Information Bottleneck Approach
In this paper, we propose a novel Multiview Variational Graph Information Bottleneck (MVGIB) principle to maximize the agreement for common representations and the disagreement for view-specific representations.
Turning Mathematics Problems into Games: Reinforcement Learning and Gröbner bases together solve Integer Feasibility Problems
The Gr\"obner basis can be seen as a set of connecting moves (actions) of the game.
Towards Understanding Mixture of Experts in Deep Learning
To our knowledge, this is the first result towards formally understanding the mechanism of the MoE layer for deep learning.
Graph Generative Model for Benchmarking Graph Neural Networks
As the field of Graph Neural Networks (GNN) continues to grow, it experiences a corresponding increase in the need for large, real-world datasets to train and test new GNN models on challenging, realistic problems.
Optimizing Video Prediction via Video Frame Interpolation
Extensive experiments on the Cityscapes, KITTI, DAVIS, Middlebury, and Vimeo90K datasets show that our video prediction results are robust in general scenarios, and our approach outperforms other video prediction methods that require a large amount of training data or extra semantic information.
Geometric Policy Iteration for Markov Decision Processes
GPI updates the policy of a single state by switching to an action that is mapped to the boundary of the value function polytope, followed by an immediate update of the value function.
Prompt-aligned Gradient for Prompt Tuning
Thanks to the large pre-trained vision-language models (VLMs) like CLIP, we can craft a zero-shot classifier by "prompt", e. g., the confidence score of an image being "[CLASS]" can be obtained by using the VLM provided similarity measure between the image and the prompt sentence "a photo of a [CLASS]".
Multi-view Point Cloud Registration based on Evolutionary Multitasking with Bi-Channel Knowledge Sharing Mechanism
The modeling of multi-view point cloud registration as multi-task optimization are twofold.
Lesion Localization in OCT by Semi-Supervised Object Detection
Over 300 million people worldwide are affected by various retinal diseases.
Real-time Online Multi-Object Tracking in Compressed Domain
Recent online Multi-Object Tracking (MOT) methods have achieved desirable tracking performance.
The China Trade Shock and the ESG Performances of US firms
Exploiting a trade policy in which US congress granted China the Permanent Normal Trade Relations and the resulting change in expected tariff rates on Chinese imports, we find that greater import competition from China leads to an increase in the US company's ESG performance.
FashionVLP: Vision Language Transformer for Fashion Retrieval With Feedback
Fashion image retrieval based on a query pair of reference image and natural language feedback is a challenging task that requires models to assess fashion related information from visual and textual modalities simultaneously.
Unsupervised cross domain learning with applications to 7 layer segmentation of OCTs
Unsupervised cross domain adaptation for OCT 7 layer segmentation and other medical applications where labeled training data is only available in a source domain and unavailable in the target domain.
ADDS: Adaptive Differentiable Sampling for Robust Multi-Party Learning
Inspired by the idea of dropout in neural networks, we introduce a network sampling strategy in the multi-party setting, which distributes different subnets of the central model to clients for updating, and the differentiable sampling rates allow each client to extract optimal local architecture from the supernet according to its private data distribution.
Adaptive Sampling for Heterogeneous Rank Aggregation from Noisy Pairwise Comparisons
In heterogeneous rank aggregation problems, users often exhibit various accuracy levels when comparing pairs of items.
Causal Triple Attention Time Series Forecasting
Time series forecasting has historically been a key area of academic research and industrial applications.
Embedding Novel Views in a Single JPEG Image
We propose a novel approach for embedding novel views in a single JPEG image while preserving the perceptual fidelity of the modified JPEG image and the restored novel views.
Towards Photorealistic Colorization by Imagination
We present a novel approach to automatic image colorization by imitating the imagination process of human experts.
Demonstration-Guided Reinforcement Learning with Learned Skills
Prior approaches for demonstration-guided RL treat every new task as an independent learning problem and attempt to follow the provided demonstrations step-by-step, akin to a human trying to imitate a completely unseen behavior by following the demonstrator's exact muscle movements.
Video Super-Resolution with Long-Term Self-Exemplars
Existing video super-resolution methods often utilize a few neighboring frames to generate a higher-resolution image for each frame.
SKFAC: Training Neural Networks With Faster Kronecker-Factored Approximate Curvature
For the fully connected layers, by utilizing the low-rank property of Kronecker factors of Fisher information matrix, our method only requires inverting a small matrix to approximate the curvature with desirable accuracy.
Feature Flow Regularization: Improving Structured Sparsity in Deep Neural Networks
Pruning is a model compression method that removes redundant parameters in deep neural networks (DNNs) while maintaining accuracy.
SKFAC:Training Neural Networks with Faster Kronecker-Factored Approximate Curvature
For the fully connected layers, by utilizing the low-rank property of Kronecker factors of Fisher information matrix, our method only requires inverting a small matrix to approximate the curvature with desirable accuracy.
CRT-Net: A Generalized and Scalable Framework for the Computer-Aided Diagnosis of Electrocardiogram Signals
Subsequently, a novel deep neural network, namely CRT-Net, is designed for the fine-grained and comprehensive representation and recognition of 1-D ECG signals.
LineCounter: Learning Handwritten Text Line Segmentation by Counting
In this paper, we propose a novel Line Counting formulation for HTLS -- that involves counting the number of text lines from the top at every pixel location.
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration.
Maximizing Mutual Information Across Feature and Topology Views for Learning Graph Representations
Specifically, we first utilize a multi-view representation learning module to better capture both local and global information content across feature and topology views on graphs.
SauvolaNet: Learning Adaptive Sauvola Network for Degraded Document Binarization
The AST module further consolidates the outputs from MWS and PWA and predicts the final adaptive threshold for each pixel location.
Spatially Self-Paced Convolutional Networks for Change Detection in Heterogeneous Images
Change detection in heterogeneous remote sensing images is a challenging problem because it is hard to make a direct comparison in the original observation spaces, and most methods rely on a set of manually labeled samples.
Style-Aware Normalized Loss for Improving Arbitrary Style Transfer
Neural Style Transfer (NST) has quickly evolved from single-style to infinite-style models, also known as Arbitrary Style Transfer (AST).
Modelling Paralinguistic Properties in Conversational Speech to Detect Bipolar Disorder and Borderline Personality Disorder
Bipolar disorder (BD) and borderline personality disorder (BPD) are two chronic mental health conditions that clinicians find challenging to distinguish based on clinical interviews, due to their overlapping symptoms.
Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation
We study reinforcement learning in an infinite-horizon average-reward setting with linear function approximation, where the transition probability function of the underlying Markov Decision Process (MDP) admits a linear form over a feature mapping of the current state, action, and next state.
VideoFlow: A Framework for Building Visual Analysis Pipelines
The past years have witnessed an explosion of deep learning frameworks like PyTorch and TensorFlow since the success of deep neural networks.
Uncertainty Weighted Offline Reinforcement Learning
Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration.
A Finite-Time Analysis of Two Time-Scale Actor-Critic Methods
In this work, we provide a non-asymptotic analysis for two time-scale actor-critic methods under non-i. i. d.
Class-agnostic Object Detection
Finally, we propose (1) baseline methods and (2) a new adversarial learning framework for class-agnostic detection that forces the model to exclude class-specific information from features used for predictions.
Ranked #99 on
Image Classification
on ObjectNet
(using extra training data)
Unsupervised Domain Adaptation for Visual Navigation
We further show that our method can be used to transfer the navigation policies learned in simulation to the real world.
Claw U-Net: A Unet-based Network with Deep Feature Concatenation for Scleral Blood Vessel Segmentation
Sturge-Weber syndrome (SWS) is a vascular malformation disease, and it may cause blindness if the patient's condition is severe.
Planimation
Planimation is a modular and extensible open source framework to visualise sequential solutions of planning problems specified in PDDL.
Learning to Detect Bipolar Disorder and Borderline Personality Disorder with Language and Speech in Non-Clinical Interviews
Bipolar disorder (BD) and borderline personality disorder (BPD) are both chronic psychiatric disorders.
Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
Despite success on a wide range of problems related to vision, generative adversarial networks (GANs) often suffer from inferior performance due to unstable training, especially for text generation.
Ranked #2 on
Text Generation
on EMNLP2017 WMT
Self-supervised Learning from a Multi-view Perspective
In particular, we propose a composite objective that bridges the gap between prior contrastive and predictive learning objectives, and introduce an additional objective term to discard task-irrelevant information.
A Finite Time Analysis of Two Time-Scale Actor Critic Methods
In this work, we provide a non-asymptotic analysis for two time-scale actor-critic methods under non-i. i. d.
Signature features with the visibility transformation
In this paper we put the visibility transformation on a clear theoretical footing and show that this transform is able to embed the effect of the absolute position of the data stream into signature features in a unified and efficient way.
Future Video Synthesis with Object Motion Prediction
We present an approach to predict future video frames given a sequence of continuous video frames in the past.
Ranked #2 on
Video Prediction
on KITTI
Game Theoretic Consequences of Resident Matching
The resident matching algorithm, Gale-Shapley, currently used by SF Match and the National Residency Match Program (NRMP), has been in use for over 50 years without fundamental alteration.
Cross-modality Person re-identification with Shared-Specific Feature Transfer
In this paper, we tackle the above limitation by proposing a novel cross-modality shared-specific feature transfer algorithm (termed cm-SSFT) to explore the potential of both the modality-shared information and the modality-specific characteristics to boost the re-identification performance.
Cross-Modality Person Re-identification
Person Re-Identification
Towards Understanding the Spectral Bias of Deep Learning
An intriguing phenomenon observed during training neural networks is the spectral bias, which states that neural networks are biased towards learning less complex functions.
Coverage-based Outlier Explanation
Existing algorithms are primarily focused on detection, that is the identification of outliers in a given dataset.
MMDetection: Open MMLab Detection Toolbox and Benchmark
In this paper, we introduce the various features of this toolbox.
ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features
To fight against real-life image forgery, which commonly involves different types and combined manipulations, we propose a unified deep neural architecture called ManTra-Net.
Large Scale Incremental Learning
We believe this is because of the combination of two factors: (a) the data imbalance between the old and new classes, and (b) the increasing number of visually similar classes.
Ranked #2 on
Incremental Learning
on ImageNet100 - 10 steps
(# M Params metric)
Unified Adversarial Invariance
We present a unified invariance framework for supervised neural networks that can induce independence to nuisance factors of data without using any nuisance annotations, but can additionally use labeled information about biasing factors to force their removal from the latent embedding for making fair predictions.
Spatially Constrained GAN for Face and Fashion Synthesis
Besides, a segmentor network is constructed to impose spatial constraints on the generator.
Rethinking Classification and Localization for Object Detection
Two head structures (i. e. fully connected head and convolution head) have been widely used in R-CNN based detectors for classification and localization tasks.
QATM: Quality-Aware Template Matching For Deep Learning
Finding a template in a search image is one of the core problems many computer vision, such as semantic image semantic, image-to-GPS verification \etc.
AIRD: Adversarial Learning Framework for Image Repurposing Detection
Image repurposing is a commonly used method for spreading misinformation on social media and online forums, which involves publishing untampered images with modified metadata to create rumors and further propaganda.
Image-to-GPS Verification Through A Bottom-Up Pattern Matching Network
The image-to-GPS verification problem asks whether a given image is taken at a claimed GPS location.
Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation
The theory gives a complete characterization of the structure of neuron activation subspace matches, where the core concepts are maximum match and simple match which describe the overall and the finest similarity between sets of neurons in two networks respectively.
Unsupervised Adversarial Invariance
Data representations that contain all the information about target variables but are invariant to nuisance factors benefit supervised learning algorithms by preventing them from learning associations between these factors and the targets, thus reducing overfitting.
VelocityGAN: Data-Driven Full-Waveform Inversion Using Conditional Adversarial Networks
Acoustic- and elastic-waveform inversion is an important and widely used method to reconstruct subsurface velocity image.
BusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization
We introduce a novel deep neural architecture for image copy-move forgery detection (CMFD), code-named BusterNet.
Deep Multimodal Image-Repurposing Detection
Nefarious actors on social media and other platforms often spread rumors and falsehoods through images whose metadata (e. g., captions) have been modified to provide visual substantiation of the rumor/falsehood.
Predictive Local Smoothness for Stochastic Gradient Methods
To address this problem, we propose a simple yet effective method for improving stochastic gradient methods named predictive local smoothness (PLS).
Facial Landmark Detection: a Literature Survey
The regression-based methods implicitly capture facial shape and appearance information.
Machine Learning for Exam Triage
In this project, we extend the state-of-the-art CheXNet (Rajpurkar et al. [2017]) by making use of the additional non-image features in the dataset.
Forecasting Future Humphrey Visual Fields Using Deep Learning
Methods: All datapoints from consecutive 24-2 HVFs from 1998 to 2018 were extracted from a University of Washington database.
Generating retinal flow maps from structural optical coherence tomography with artificial intelligence
Despite significant advances in artificial intelligence (AI) for computer vision, its application in medical imaging has been limited by the burden and limits of expert-generated labels.
CapsuleGAN: Generative Adversarial Capsule Network
We provide guidelines for designing CapsNet discriminators and the updated GAN objective function, which incorporates the CapsNet margin loss, for training CapsuleGAN models.
Incremental Classifier Learning with Generative Adversarial Networks
To address these problems, we propose (a) a new loss function to combine the cross-entropy loss and distillation loss, (b) a simple way to estimate and remove the unbalance between the old and new classes , and (c) using Generative Adversarial Networks (GANs) to generate historical data and select representative exemplars during generation.
MRI Tumor Segmentation with Densely Connected 3D CNN
The major difficulty of our segmentation model comes with the fact that the location, structure, and shape of gliomas vary significantly among different patients.
Seismic-Net: A Deep Densely Connected Neural Network to Detect Seismic Events
In particular, we demonstrate the efficacy of our Seismic-Net by formulating our detection problem as an event detection problem with time series data.
Clustering with Outlier Removal
Then an objective function based Holoentropy is designed to enhance the compactness of each cluster with a few outliers removed.
Bidirectional Conditional Generative Adversarial Networks
Conditional Generative Adversarial Networks (cGANs) are generative models that can produce data samples ($x$) conditioned on both latent variables ($z$) and known auxiliary information ($c$).
Self-Organized Text Detection With Minimal Post-Processing via Border Learning
In this paper we propose a new solution to the text detection problem via border learning.
Constrained Joint Cascade Regression Framework for Simultaneous Facial Action Unit Recognition and Facial Landmark Detection
Experimental results demonstrate that the intertwined relationships of facial action units and face shapes boost the performances of both facial action unit recognition and facial landmark detection.
Robust Facial Landmark Detection under Significant Head Poses and Occlusion
In this work, we propose a unified robust cascade regression framework that can handle both images with severe occlusion and images with large head poses.
Constrained Deep Transfer Feature Learning and its Applications
Furthermore, we propose to exploit the target domain knowledge and incorporate such prior knowledge as a constraint during transfer learning to ensure that the transferred data satisfies certain properties of the target domain.
Simultaneous Facial Landmark Detection, Pose and Deformation Estimation under Facial Occlusion
Facial landmark detection, head pose estimation, and facial deformation analysis are typical facial behavior analysis tasks in computer vision.
A Hierarchical Probabilistic Model for Facial Feature Detection
Facial feature detection from facial images has attracted great attention in the field of computer vision.
Facial Feature Tracking under Varying Facial Expressions and Face Poses based on Restricted Boltzmann Machines
To handle pose variations, the frontal face shape prior model is incorporated into a 3-way RBM model that could capture the relationship between frontal face shapes and non-frontal face shapes.
Cascaded Region-based Densely Connected Network for Event Detection: A Seismic Application
Because of the fact that some positive events are not correctly annotated, we further formulate the detection problem as a learning-from-noise problem.
Deep Matching and Validation Network -- An End-to-End Solution to Constrained Image Splicing Localization and Detection
Here the task is to estimate the probability that the donor image has been used to splice the query image, and obtain the splicing masks for both the query and donor images.
SOL: A Library for Scalable Online Learning Algorithms
SOL is an open-source library for scalable online learning algorithms, and is particularly suitable for learning with high-dimensional data.
Multimodal Spontaneous Emotion Corpus for Human Behavior Analysis
The corpus further includes derived features from 3D, 2D, and IR (infrared) sensors and baseline results for facial expression and action unit detection.
Families in the Wild (FIW): Large-Scale Kinship Image Database and Benchmarks
Motivated by the lack of a single, unified dataset for kinship recognition, we aim to provide a dataset that captivates the interest of the research community.
Relaxing From Vocabulary: Robust Weakly-Supervised Deep Learning for Vocabulary-Free Image Tagging
The development of deep learning has empowered machines with comparable capability of recognizing limited image categories to human beings.
Facial Landmark Detection with Tweaked Convolutional Neural Networks
We present a novel convolutional neural network (CNN) design for facial landmark coordinate regression.
LOGO-Net: Large-scale Deep Logo Detection and Brand Recognition with Deep Region-based Convolutional Networks
In this paper, we introduce "LOGO-Net", a large-scale logo image database for logo detection and brand recognition from real-world product images.
Learning Document Image Binarization from Data
In this paper we present a fully trainable binarization solution for degraded document images.
Large-scale Online Feature Selection for Ultra-high Dimensional Sparse Data
However, unlike many second-order learning methods that often suffer from extra high computational cost, we devise a novel smart algorithm for second-order online feature selection using a MaxHeap-based approach, which is not only more effective than the existing first-order approaches, but also significantly more efficient and scalable for large-scale feature selection with ultra-high dimensional sparse data, as validated from our extensive experiments.
Gaussian Process Volatility Model
A Gaussian Process (GP) defines a distribution over functions, which allows us to capture highly flexible functional relationships for the variances.
Blockwise SURE Shrinkage for Non-Local Means
In this letter, we investigate the shrinkage problem for the non-local means (NLM) image denoising.
Dynamic Covariance Models for Multivariate Financial Time Series
The accurate prediction of time-changing covariances is an important problem in the modeling of multivariate financial data.
