Search Results for author:
Found 93 papers, 22 papers with code
Capturing Conversational Interaction for Question Answering via Global History Reasoning
Conversational Question Answering (ConvQA) is required to answer the current question, conditioned on the observable paragraph-level context and conversation history.
Two-shot Video Object Segmentation
The underlying idea is to generate pseudo labels for unlabeled frames during training and to optimize the model on the combination of labeled and pseudo-labeled data.
Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction
The Multiplane Image (MPI), containing a set of fronto-parallel RGBA layers, is an effective and efficient representation for view synthesis from sparse inputs.
A Comparative Study of Deep Learning and Iterative Algorithms for Joint Channel Estimation and Signal Detection
Joint channel estimation and signal detection (JCESD) is crucial in wireless communication systems, but traditional algorithms perform poorly in low signal-to-noise ratio (SNR) scenarios.
Anchor-Based Adversarially Robust Zero-Shot Learning Driven by Language
LAAT uses a text encoder to obtain fixed anchors (normalized feature embeddings) of each category, then uses these anchors to perform adversarial training.
Distributed Stochastic Optimization under a General Variance Condition
Distributed stochastic optimization has drawn great attention recently due to its effectiveness in solving large-scale machine learning problems.
An Efficient Semi-Automated Scheme for Infrastructure LiDAR Annotation
Specifically, we introduce a human-in-the-loop schema in which annotators recursively fix and refine annotations imperfectly predicted by our tool and incrementally add them to the training dataset to obtain better SOT and MOT models.
A Provable Splitting Approach for Symmetric Nonnegative Matrix Factorization
The symmetric Nonnegative Matrix Factorization (NMF), a special but important class of the general NMF, has found numerous applications in data analysis such as various clustering tasks.
Principled and Efficient Transfer Learning of Deep Models via Neural Collapse
As model size continues to grow and access to labeled training data remains limited, transfer learning has become a popular approach in many scientific and engineering fields.
Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networks
The first stage of ROCK corresponds to the process of decomposing objects into parts in human vision.
DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data
Numerical reasoning over hybrid data containing tables and long texts has recently received research attention from the AI community.
Estimating Neural Reflectance Field from Radiance Field using Tree Structures
A high-quality NeRF decomposition relies on good geometry information extraction as well as good prior terms to properly resolve ambiguities between different components.
Are All Losses Created Equal: A Neural Collapse Perspective
We extend such results and show through global solution and landscape analyses that a broad family of loss functions including commonly used label smoothing (LS) and focal loss (FL) exhibits Neural Collapse.
Neural Capture of Animatable 3D Human from Monocular Video
We present a novel paradigm of building an animatable 3D human representation from a monocular video input, such that it can be rendered in any unseen poses and views.
On the Privacy Effect of Data Enhancement via the Lens of Memorization
Many works have investigated the effect of widely-adopted data augmentation (DA) and adversarial training (AT) techniques, termed data enhancement in the paper, on the privacy leakage of machine learning models.
R^2VOS: Robust Referring Video Object Segmentation via Relational Multimodal Cycle Consistency
We leverage the cycle consistency to discriminate the semantic consensus, thus advancing the primary task.
Ranked #5 on
Referring Expression Segmentation
on Refer-YouTube-VOS (2021 public validation)
(using extra training data)
Referring Expression Segmentation
Referring Video Object Segmentation
+2
Randomized Coordinate Subgradient Method for Nonsmooth Optimization
In this work, we propose to utilize the {Randomized Coordinate Subgradient Method} (RCS) for solving both nonsmooth convex and nonsmooth nonconvex (nonsmooth weakly convex) optimization problems.
AI for CSI Feedback Enhancement in 5G-Advanced
This article provides a guideline for the standardization study of AI-based CSI feedback enhancement.
Finite-Time Analysis of Fully Decentralized Single-Timescale Actor-Critic
Most of the existing finite-time convergence results are derived based on either double-loop update or two-timescale step sizes rule, and this is the case even for centralized AC algorithm under a single-agent setting.
A Unified Convergence Theorem for Stochastic Optimization Methods
In this work, we provide a fundamental unified convergence theorem used for deriving expected and almost sure convergence results for a series of stochastic optimization methods.
AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension
Recent machine reading comprehension datasets such as ReClor and LogiQA require performing logical reasoning over text.
On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features
When training deep neural networks for classification tasks, an intriguing empirical phenomenon has been widely observed in the last-layer classifiers and features, where (i) the class means and the last-layer classifiers all collapse to the vertices of a Simplex Equiangular Tight Frame (ETF) up to scaling, and (ii) cross-example within-class variability of last-layer activations collapses to zero.
Distributed Random Reshuffling over Networks
We show that D-RR inherits favorable characteristics of RR for both smooth strongly convex and smooth nonconvex objective functions.
Reliable Propagation-Correction Modulation for Video Object Segmentation
We introduce two modulators, propagation and correction modulators, to separately perform channel-wise re-calibration on the target frame embeddings according to local temporal correlations and reliable references respectively.
Semantic Segmentation
Semi-Supervised Video Object Segmentation
+1
Hybrid Instance-aware Temporal Fusion for Online Video Instance Segmentation
Based on this representation, we introduce a cropping-free temporal fusion approach to model the temporal consistency between video frames.
BarrierNet: A Safety-Guaranteed Layer for Neural Networks
This paper introduces differentiable higher-order control barrier functions (CBF) that are end-to-end trainable together with learning systems.
Video Instance Segmentation by Instance Flow Assembly
Instance segmentation is a challenging task aiming at classifying and segmenting all object instances of specific classes.
Convergence of Random Reshuffling Under The Kurdyka-Łojasiewicz Inequality
We conduct a novel convergence analysis for the non-descent RR method with diminishing step sizes based on the KL inequality, which generalizes the standard KL framework.
SeanNet: Semantic Understanding Network for Localization Under Object Dynamics
This paper proposes a SEmantic understANding Network (SeanNet) architecture that enables an effective learning process with coupled visual and semantic inputs.
Randomized Primal-Dual Coordinate Method for Large-scale Linearly Constrained Nonsmooth Nonconvex Optimization
The large-scale linearly constrained nonsmooth nonconvex optimization finds wide applications in machine learning, including non-PSD Kernel SVM, linearly constrained Lasso with nonsmooth nonconvex penalty, etc.
End-to-End Video Object Detection with Spatial-Temporal Transformers
Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors.
Attention-Based 3D Seismic Fault Segmentation Training by a Few 2D Slice Labels
The task of image segmentation requires huge labels, especially 3D seismic data, which has a complex structure and lots of noise.
A Geometric Analysis of Neural Collapse with Unconstrained Features
In contrast to existing landscape analysis for deep neural networks which is often disconnected from practice, our analysis of the simplified model not only does it explain what kind of features are learned in the last layer, but it also shows why they can be efficiently optimized in the simplified settings, matching the empirical observations in practical deep network architectures.
Out-of-Step Detection Based On an Improved Line Potential Energy Criterion
The line potential energy in the cutset is used as the criterion for monitoring the generator instability, but the criterion has the following two limitations due to narrowly defined conditions.
Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation
Tremendous efforts have been made on instance segmentation but the mask quality is still not satisfactory.
Sensing population distribution from satellite imagery via deep learning: model selection, neighboring effect, and systematic biases
The rapid development of remote sensing techniques provides rich, large-coverage, and high-temporal information of the ground, which can be coupled with the emerging deep learning approaches that enable latent features and hidden geographical patterns to be extracted.
Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training
Furthermore, we show that our ConvNorm can reduce the layerwise spectral norm of the weight matrices and hence improve the Lipschitzness of the network, leading to easier training and improved robustness for deep ConvNets.
The Logical Options Framework
Learning composable policies for environments with complex rules and tasks is a challenging problem.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Provable Boolean Interaction Recovery from Tree Ensemble obtained via Random Forests
Iterative Random Forests (iRF) use a tree ensemble from iteratively modified RF to obtain predictive and stable non-linear or Boolean interactions of features.
Statistics Theory Statistics Theory
Rethinking Natural Adversarial Examples for Classification Models
A detection model based on the classification model EfficientNet-B7 achieved a top-1 accuracy of 53. 95%, surpassing previous state-of-the-art classification models trained on ImageNet, suggesting that accurate localization information can significantly boost the performance of classification models on ImageNet-A.
Stability of scar states in 2D PXP model against random disorders
Recently a class of quantum systems exhibiting weak ergodicity breaking has attracted much attention.
Disordered Systems and Neural Networks Statistical Mechanics
Hybrid Beamforming for mmWave MU-MISO Systems Exploiting Multi-agent Deep Reinforcement Learning
In this letter, we investigate the hybrid beamforming based on deep reinforcement learning (DRL) for millimeter Wave (mmWave) multi-user (MU) multiple-input-single-output (MISO) system.
Fooling thermal infrared pedestrian detectors in real world using small bulbs
We propose a physical attack method with small bulbs on a board against the state of-the-art pedestrian detectors.
TSQA: Tabular Scenario Based Question Answering
To solve the task, we extend state-of-the-art MRC methods with TTGen, a novel table-to-text generator.
Using a Penalty-based Loss Re-estimation Method to Improve Implicit Discourse Relation Classification
We tackle implicit discourse relation classification, a task of automatically determining semantic relationships between arguments.
A Bayesian Nonparametric model for textural pattern heterogeneity
Cancer radiomics is an emerging discipline promising to elucidate lesion phenotypes and tumor heterogeneity through patterns of enhancement, texture, morphology, and shape.
Applications
Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation
The Variational Autoencoder (VAE) is a popular and powerful model applied to text modelling to generate diverse sentences.
DGST: a Dual-Generator Network for Text Style Transfer
We propose DGST, a novel and simple Dual-Generator network architecture for text Style Transfer.
Integrated Communication and Localization in mmWave Systems
As the fifth-generation (5G) mobile communication system is being commercialized, extensive studies on the evolution of 5G and sixth-generation mobile communication systems have been conducted.
A Blockchain Transaction Graph based Machine Learning Method for Bitcoin Price Prediction
Bitcoin, as one of the most popular cryptocurrency, is recently attracting much attention of investors.
Multi-Task Neural Model for Agglutinative Language Translation
Neural machine translation (NMT) has achieved impressive performance recently by using large-scale parallel corpora.
Distribution Aligned Multimodal and Multi-Domain Image Stylization
Currently, there are few methods that can perform both multimodal and multi-domain stylization simultaneously.
Curating a COVID-19 data repository and forecasting county-level death counts in the United States
We use this data to develop predictions and corresponding prediction intervals for the short-term trajectory of COVID-19 cumulative death counts at the county-level in the United States up to two weeks ahead.
A Text Reassembling Approach to Natural Language Generation
Recent years have seen a number of proposals for performing Natural Language Generation (NLG) based in large part on statistical techniques.
Geometric Analysis of Nonconvex Optimization Landscapes for Overcomplete Learning
Learning overcomplete representations finds many applications in machine learning and data analytics.
An Early Study on Intelligent Analysis of Speech under COVID-19: Severity, Sleep Quality, Fatigue, and Anxiety
In particular, by analysing speech recordings from these patients, we construct audio-only-based models to automatically categorise the health state of patients from four aspects, including the severity of illness, sleep quality, fatigue, and anxiety.
Deep Reinforcement Learning for Adaptive Learning Systems
In this paper, we formulate the adaptive learning problem---the problem of how to find an individualized learning plan (called policy) that chooses the most appropriate learning materials based on learner's latent traits---faced in adaptive learning systems as a Markov decision process (MDP).
COVID-19 and Computer Audition: An Overview on What Speech & Sound Analysis Could Contribute in the SARS-CoV-2 Corona Crisis
We come to the conclusion that CA appears ready for implementation of (pre-)diagnosis and monitoring tools, and more generally provides rich and significant, yet so far untapped potential in the fight against COVID-19 spread.
Finding the Sparsest Vectors in a Subspace: Theory, Algorithms, and Applications
The problem of finding the sparsest vector (direction) in a low dimensional subspace can be considered as a homogeneous variant of the sparse recovery problem, which finds applications in robust subspace recovery, dictionary learning, sparse blind deconvolution, and many other problems in signal processing and machine learning.
Morphological Word Segmentation on Agglutinative Languages for Neural Machine Translation
Experimental results show that our morphologically motivated word segmentation method is better suitable for the NMT model, which achieves significant improvements on Turkish-English and Uyghur-Chinese machine translation tasks on account of reducing data sparseness and language complexity.
MIMO Transmission through Reconfigurable Intelligent Surface: System Design, Analysis, and Implementation
Reconfigurable intelligent surface (RIS) is a new paradigm that has great potential to achieve cost-effective, energy-efficient information modulation for wireless transmission, by the ability to change the reflection coefficients of the unit cells of a programmable metasurface.
Analysis of the Optimization Landscapes for Overcomplete Representation Learning
In this work, we show these problems can be formulated as $\ell^4$-norm optimization problems with spherical constraint, and study the geometric properties of their nonconvex optimization landscapes.
A Stable Variational Autoencoder for Text Modelling
Variational Autoencoder (VAE) is a powerful method for learning representations of high-dimensional data.
Weakly Convex Optimization over Stiefel Manifold Using Riemannian Subgradient-Type Methods
To the best of our knowledge, these are the first convergence guarantees for using Riemannian subgradient-type methods to optimize a class of nonconvex nonsmooth functions over the Stiefel manifold.
Physical Layer Security Enhancement Exploiting Intelligent Reflecting Surface
In this letter, the use of intelligent reflecting surface (IRS) to enhance the physical layer security of downlink wireless communication is investigated.
A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution
We study the multi-channel sparse blind deconvolution (MCS-BD) problem, whose task is to simultaneously recover a kernel $\mathbf a$ and multiple sparse inputs $\{\mathbf x_i\}_{i=1}^p$ from their circulant convolution $\mathbf y_i = \mathbf a \circledast \mathbf x_i $ ($i=1,\cdots, p$).
GeoSQA: A Benchmark for Scenario-based Question Answering in the Geography Domain at High School Level
Scenario-based question answering (SQA) has attracted increasing research attention.
PrecoderNet: Hybrid Beamforming for Millimeter Wave Systems with Deep Reinforcement Learning
In this letter, we investigate the hybrid beamforming for millimeter wave massive multiple-input multiple-output (MIMO) system based on deep reinforcement learning (DRL).
Latent Space Factorisation and Manipulation via Matrix Subspace Projection
We demonstrate the utility of our method for attribute manipulation in autoencoders trained across varied domains, using both human evaluation and automated methods.
Ranked #7 on
Image Generation
on CelebA 256x256
(FID metric)
A Debiased MDI Feature Importance Measure for Random Forests
Based on the original definition of MDI by Breiman et al. for a single tree, we derive a tight non-asymptotic bound on the expected bias of MDI importance of noisy features, showing that deep trees have higher (expected) feature selection bias than shallow ones.
Synthesizing 3D Shapes from Silhouette Image Collections using Multi-projection Generative Adversarial Networks
Key to our method is a novel multi-projection generative adversarial network (MP-GAN) that trains a 3D shape generator to be consistent with multiple 2D projections of the 3D shapes, and without direct access to these 3D shapes.
Automata Guided Skill Composition
Skills learned through (deep) reinforcement learning often generalizes poorly across tasks and re-training is necessary when presented with a new task.
Arbitrage of Energy Storage in Electricity Markets with Deep Reinforcement Learning
In this letter, we address the problem of controlling energy storage systems (ESSs) for arbitrage in real-time electricity markets under price uncertainty.
Mimicking the In-Camera Color Pipeline for Camera-Aware Object Compositing
We present a method for compositing virtual objects into a photograph such that the object colors appear to have been processed by the photo's camera imaging pipeline.
Temporal Logic Guided Safe Reinforcement Learning Using Control Barrier Functions
We combine temporal logic with control Lyapunov functions to improve exploration.
Dropping Symmetry for Fast Symmetric Nonnegative Matrix Factorization
Symmetric nonnegative matrix factorization (NMF), a special but important class of the general NMF, is demonstrated to be useful for data analysis and in particular for various clustering tasks.
Statistical NLG for Generating the Content and Form of Referring Expressions
This paper argues that a new generic approach to statistical NLG can be made to perform Referring Expression Generation (REG) successfully.
A Dual-Attention Hierarchical Recurrent Neural Network for Dialogue Act Classification
Recognising dialogue acts (DA) is important for many natural language processing tasks such as dialogue generation and intention recognition.
Ranked #4 on
Dialogue Act Classification
on Switchboard corpus
Optimal Hierarchical Learning Path Design with Reinforcement Learning
To this end, we first develop a model for students' hierarchical skills in the E-learning system.
Nonconvex Robust Low-rank Matrix Recovery
In this paper we study the problem of recovering a low-rank matrix from a number of random linear measurements that are corrupted by outliers taking arbitrary values.
Information Theory Information Theory
Automata Guided Reinforcement Learning With Demonstrations
Tasks with complex temporal structures and long horizons pose a challenge for reinforcement learning agents due to the difficulty in specifying the tasks in terms of reward functions as well as large variances in the learning signals.
AUTOMATA GUIDED HIERARCHICAL REINFORCEMENT LEARNING FOR ZERO-SHOT SKILL COMPOSITION
An obstacle that prevents the wide adoption of (deep) reinforcement learning (RL) in control systems is its need for a large number of interactions with the environment in order to master a skill.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Automata-Guided Hierarchical Reinforcement Learning for Skill Composition
Skills learned through (deep) reinforcement learning often generalizes poorly across domains and re-training is necessary when presented with a new task.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
A Policy Search Method For Temporal Logic Specified Reinforcement Learning Tasks
In this paper, we explore the use of temporal logic (TL) to specify tasks in reinforcement learning.
Optimized Structured Sparse Sensing Matrices for Compressive Sensing
We consider designing a robust structured sparse sensing matrix consisting of a sparse matrix with a few non-zero entries per row and a dense base matrix for capturing signals efficiently We design the robust structured sparse sensing matrix through minimizing the distance between the Gram matrix of the equivalent dictionary and the target Gram of matrix holding small mutual coherence.
Log-linear Models for Uyghur Segmentation in Spoken Language Translation
To alleviate data sparsity in spoken Uyghur machine translation, we proposed a log-linear based morphological segmentation approach.
Investigating the content and form of referring expressions in Mandarin: introducing the Mtuna corpus
East Asian languages are thought to handle reference differently from languages such as English, particularly in terms of the marking of definiteness and number.
Reinforcement Learning With Temporal Logic Rewards
We propose Truncated Linear Temporal Logic (TLTL) as specifications language, that is arguably well suited for the robotics applications, together with quantitative semantics, i. e., robustness degree.
A Hierarchical Reinforcement Learning Method for Persistent Time-Sensitive Tasks
Reinforcement learning has been applied to many interesting problems such as the famous TD-gammon and the inverted helicopter flight.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
An Active Learning Framework using Sparse-Graph Codes for Sparse Polynomials and Graph Sketching
By writing the cut function as a polynomial and exploiting the graph structure, we propose a sketching algorithm to learn the an arbitrary $n$-node unknown graph using only few cut queries, which scales {\it almost linearly} in the number of edges and {\it sub-linearly} in the graph size $n$.
SPRIGHT: A Fast and Robust Framework for Sparse Walsh-Hadamard Transform
We consider the problem of computing the Walsh-Hadamard Transform (WHT) of some $N$-length input vector in the presence of noise, where the $N$-point Walsh spectrum is $K$-sparse with $K = {O}(N^{\delta})$ scaling sub-linearly in the input dimension $N$ for some $0<\delta<1$.
