Search Results for author:
Found 91 papers, 30 papers with code
DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset
This paper describes in detail the construction process and data statistics of DuSQL.
ModWaveMLP: MLP-Based Mode Decomposition and Wavelet Denoising Model to Defeat Complex Structures in Traffic Forecasting
Additionally, when handling traffic data, researchers tend to manually design the model structure based on the data features, which makes the structure of traffic prediction redundant and the model generalizability limited.
DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysis
The rapid progress in deep learning has given rise to hyper-realistic facial forgery methods, leading to concerns related to misinformation and security risks.
Balancing Enhancement, Harmlessness, and General Capabilities: Enhancing Conversational LLMs with Direct RLHF
This process often leads to issues such as forgetting or a decrease in the base model's abilities.
SISSA: Real-time Monitoring of Hardware Functional Safety and Cybersecurity with In-vehicle SOME/IP Ethernet Traffic
Scalable service-Oriented Middleware over IP (SOME/IP) is an Ethernet communication standard protocol in the Automotive Open System Architecture (AUTOSAR), promoting ECU-to-ECU communication over the IP stack.
Tradeoffs of Diagonal Fisher Information Matrix Estimators
The Fisher information matrix characterizes the local geometry in the parameter space of neural networks.
ICE-GRT: Instruction Context Enhancement by Generative Reinforcement based Transformers
The emergence of Large Language Models (LLMs) such as ChatGPT and LLaMA encounter limitations in domain-specific tasks, with these models often lacking depth and accuracy in specialized areas, and exhibiting a decrease in general capabilities when fine-tuned, particularly analysis ability in small sized models.
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
Character Animation aims to generating character videos from still images through driving signals.
Magmaw: Modality-Agnostic Adversarial Attacks on Machine Learning-Based Wireless Communication Systems
Although there have been a number of adversarial attacks on ML-based wireless systems, the existing methods do not provide a comprehensive view including multi-modality of the source data, common physical layer components, and wireless domain constraints.
Balancing Specialized and General Skills in LLMs: The Impact of Modern Tuning and Data Strategy
This paper introduces a multifaceted methodology for fine-tuning and evaluating large language models (LLMs) for specialized monetization tasks.
Continual Face Forgery Detection via Historical Distribution Preserving
In this paper, we focus on a novel and challenging problem: Continual Face Forgery Detection (CFFD), which aims to efficiently learn from new forgery attacks without forgetting previous ones.
Cloth2Tex: A Customized Cloth Texture Generation Pipeline for 3D Virtual Try-On
Since traditional warping-based texture generation methods require a significant number of control points to be manually selected for each type of garment, which can be a time-consuming and tedious process.
Towards General Visual-Linguistic Face Forgery Detection
To address this issues, in this paper, we propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Models
Due to the stochastic sampling process of diffusion, our model is capable of sampling multiple possible predictions from the mask distribution, avoiding the problem of overconfident point estimation.
Gloss-Free End-to-End Sign Language Translation
In this paper, we tackle the problem of sign language translation (SLT) without gloss annotations.
InterFormer: Real-time Interactive Image Segmentation
Interactive image segmentation enables annotators to efficiently perform pixel-level annotation for segmentation tasks.
Mathematical Challenges in Deep Learning
Deep models are dominating the artificial intelligence (AI) industry since the ImageNet challenge in 2012.
Transformed Distribution Matching for Missing Value Imputation
The key to missing value imputation is to capture the data distribution with incomplete samples and impute the missing values accordingly.
$2 \times 2$ Zero-Sum Games with Commitments and Noisy Observations
In this paper, $2\times2$ zero-sum games are studied under the following assumptions: $(1)$ One of the players (the leader) commits to choose its actions by sampling a given probability measure (strategy); $(2)$ The leader announces its action, which is observed by its opponent (the follower) through a binary channel; and $(3)$ the follower chooses its strategy based on the knowledge of the leader's strategy and the noisy observation of the leader's action.
How Does Value Distribution in Distributional Reinforcement Learning Help Optimization?
We consider the problem of learning a set of probability distributions from the Bellman dynamics in distributional reinforcement learning~(RL) that learns the whole return distribution compared with only its expectation in classical RL.
Distributional Reinforcement Learning
reinforcement-learning
+1
Non-linear Embeddings in Hilbert Simplex Geometry
A key technique of machine learning and computer vision is to embed discrete weighted graphs into continuous spaces for further downstream processing.
RTGNN: A Novel Approach to Model Stochastic Traffic Dynamics
Because it is difficult to develop first principle models of cars driven by humans, there is great potential for using data driven approaches in developing traffic dynamical models.
Distributional Reinforcement Learning by Sinkhorn Divergence
The empirical success of distributional reinforcement learning~(RL) highly depends on the distribution representation and the choice of distribution divergence.
Fair Wrapping for Black-box Predictions
We introduce a new family of techniques to post-process ("wrap") a black-box classifier in order to reduce its bias.
Contrastive Laplacian Eigenmaps
Starting from a GAN-inspired contrastive formulation, we show that the Jensen-Shannon divergence underlying many contrastive graph embedding models fails under disjoint positive and negative distributions, which may naturally emerge during sampling in the contrastive setting.
Dual Contrastive Learning for General Face Forgery Detection
With various facial manipulation techniques arising, face forgery detection has drawn growing attention due to security concerns.
Pareto Adversarial Robustness: Balancing Spatial Robustness and Sensitivity-based Robustness
In this paper, we endeavor to design strategies to achieve universal adversarial robustness.
Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilization
Anderson mixing has been heuristically applied to reinforcement learning (RL) algorithms for accelerating convergence and improving the sampling efficiency of deep RL.
High-order Tensor Pooling with Attention for Action Recognition
We aim at capturing high-order statistics of feature vectors formed by a neural network, and propose end-to-end second- and higher-order pooling to form a tensor descriptor.
Ranked #2 on
Scene Recognition
on YUP++
(using extra training data)
The Benefits of Being Categorical Distributional: Uncertainty-aware Regularized Exploration in Reinforcement Learning
The theoretical advantages of distributional reinforcement learning~(RL) over classical RL remain elusive despite its remarkable empirical performance.
Exploring the Robustness of Distributional Reinforcement Learning against Noisy State Observations
In real scenarios, state observations that an agent observes may contain measurement errors or adversarial noises, misleading the agent to take suboptimal actions or even collapse while training.
Distributional Reinforcement Learning
reinforcement-learning
+1
Towards Understanding Distributional Reinforcement Learning: Regularization, Optimization, Acceleration and Sinkhorn Algorithm
Distributional reinforcement learning~(RL) is a class of state-of-the-art algorithms that estimate the whole distribution of the total return rather than only its expectation.
Gaussian Differential Privacy Transformation: from identification to application
Gaussian differential privacy (GDP) is a single-parameter family of privacy notions that provides coherent guarantees to avoid the exposure of individuals from machine learning models.
A Simple Unified Framework for Anomaly Detection in Deep Reinforcement Learning
In this paper, we propose a simple yet effective anomaly detection framework for deep RL algorithms that simultaneously considers random, adversarial and out-of-distribution~(OOD) state outliers.
Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observations
In real scenarios, state observations that an agent observes may contain measurement errors or adversarial noises, misleading the agent to take suboptimal actions or even collapse while training.
On the Variance of the Fisher Information for Deep Learning
In the realm of deep learning, the Fisher information matrix (FIM) gives novel insights and useful tools to characterize the loss landscape, perform second-order optimization, and build geometric learning theories.
Secure Quantized Training for Deep Learning
We implement training of neural networks in secure multi-party computation (MPC) using quantization commonly used in said setting.
Intent Disentanglement and Feature Self-supervision for Novel Recommendation
Improving the recommendation of tail items can promote novelty and bring positive effects to both users and providers, and thus is a desirable property of recommender systems.
Graph Learning: A Survey
In this survey, we present a comprehensive overview on the state-of-the-art of graph learning.
Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression
Our motivation is that regressing keypoint positions accurately needs to learn representations that focus on the keypoint regions.
Network Representation Learning: From Traditional Feature Learning to Deep Learning
Network representation learning (NRL) is an effective graph analytics technique and promotes users to deeply understand the hidden characteristics of graph data.
Synergy Between Semantic Segmentation and Image Denoising via Alternate Boosting
We observe that not only denoising helps combat the drop of segmentation accuracy due to noise, but also pixel-wise semantic information boosts the capability of denoising.
Effectiveness of MPC-friendly Softmax Replacement
Softmax is widely used in deep learning to map some representation to a probability distribution.
A Practical Chinese Dependency Parser Based on A Large-scale Dataset
DDParser is extended on the graph-based biaffine parser to accommodate to the characteristics of Chinese dataset.
Multivariate Relations Aggregation Learning in Social Networks
Therefore, in graph learning tasks of social networks, the identification and utilization of multivariate relationship information are more important.
Feedback Enhanced Motion Planning for Autonomous Vehicles
In this work, we address the motion planning problem for autonomous vehicles through a new lattice planning approach, called Feedback Enhanced Lattice Planner (FELP).
Robotics
Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint Estimates
The typical bottom-up human pose estimation framework includes two stages, keypoint detection and grouping.
Classify and Generate Reciprocally: Simultaneous Positive-Unlabelled Learning and Conditional Generation with Extra Data
The scarcity of class-labeled data is a ubiquitous bottleneck in many machine learning problems.
Seq2seq Translation Model for Sequential Recommendation
We then generalize recent advancements in translation model from sequences of words in two languages to sequences of items and contexts in recommender systems.
Information-Geometric Set Embeddings (IGSE): From Sets to Probability Distributions
This letter introduces an abstract learning problem called the "set embedding": The objective is to map sets into probability distributions so as to lose less information.
Patch-level Neighborhood Interpolation: A General and Effective Graph-based Regularization Strategy
Regularization plays a crucial role in machine learning models, especially for deep neural networks.
A Note on Our Submission to Track 4 of iDASH 2019
iDASH is a competition soliciting implementations of cryptographic schemes of interest in the context of biology.
Deep High-Resolution Representation Learning for Visual Recognition
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection.
Ranked #1 on
Object Detection
on COCO test-dev
(Hardware Burden metric)
AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models
The design of deep graph models still remains to be investigated and the crucial part is how to explore and exploit the knowledge from different hops of neighbors in an efficient way.
Ranked #2 on
Node Classification
on MS ACADEMIC
Learning Deep Image Priors for Blind Image Denoising
In this paper, we propose an effective image denoising method by learning two image priors from the perspective of domain alignment.
Improving Variational Autoencoder with Deep Feature Consistent and Generative Adversarial Training
We present a new method for improving the performances of variational autoencoder (VAE).
A Geometric Modeling of Occam's Razor in Deep Learning
Why do deep neural networks (DNNs) benefit from very high dimensional parameter spaces?
High-Resolution Representations for Labeling Pixels and Regions
The proposed approach achieves superior results to existing single-model networks on COCO object detection.
Ranked #7 on
Semantic Segmentation
on LIP val
Fisher-Bures Adversary Graph Convolutional Networks
We try to minimize the loss wrt the perturbed $G+\Delta{G}$ while making $\Delta{G}$ to be effective in terms of the Fisher information of the neural network.
Virtual Adversarial Training on Graph Convolutional Networks in Node Classification
The effectiveness of Graph Convolutional Networks (GCNs) has been demonstrated in a wide range of graph-based machine learning tasks.
Enhancing the Robustness of Deep Neural Networks by Boundary Conditional GAN
In this work, we propose a novel defense mechanism called Boundary Conditional GAN to enhance the robustness of deep neural networks against adversarial examples.
Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labels
In this paper, we propose a novel training algorithm for Graph Convolutional Network, called Multi-Stage Self-Supervised(M3S) Training Algorithm, combined with self-supervised learning approach, focusing on improving the generalization performance of GCNs on graphs with few labeled nodes.
Towards Understanding Adversarial Examples Systematically: Exploring Data Size, Task and Model Factors
In this paper, we present a systematic study on adversarial examples from three aspects: the amount of training data, task-dependent and model-specific factors.
Deep High-Resolution Representation Learning for Human Pose Estimation
We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworks in parallel.
Ranked #1 on
Pose Estimation
on BRACE
Relative Geometry-Aware Siamese Neural Network for 6DOF Camera Relocalization
6DOF camera relocalization is an important component of autonomous driving and navigation.
On The Chain Rule Optimal Transport Distance
We experimentally evaluate our new family of distances by quantifying the upper bounds of several jointly convex distances between statistical mixtures, and by proposing a novel efficient method to learn Gaussian mixture models (GMMs) by simplifying kernel density estimators with respect to our distance.
Representation Learning of Compositional Data
Our approach combines the benefits of the log-ratio transformation from compositional data analysis and exponential family PCA.
Intrinsic Universal Measurements of Non-linear Embeddings
We try to make a formal definition on the amount of information imposed by a non-linear mapping $f$.
Stochastic 2-D Motion Planning with a POMDP Framework
Motion planning is challenging when it comes to the case of imperfect state information.
Robotics
Chinese Lexical Analysis with Deep Bi-GRU-CRF Network
Lexical analysis is believed to be a crucial step towards natural language understanding and has been widely studied.
Guaranteed Deterministic Bounds on the Total Variation Distance between Univariate Mixtures
The total variation distance is a core statistical distance between probability measures that satisfies the metric axioms, with value always falling in $[0, 1]$.
q-Neurons: Neuron Activations based on Stochastic Jackson's Derivative Operators
We propose a new generic type of stochastic neurons, called $q$-neurons, that considers activation functions based on Jackson's $q$-derivatives with stochastic parameters $q$.
IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks
In this paper, we are interested in building lightweight and efficient convolutional neural networks.
Frank-Wolfe Network: An Interpretable Deep Structure for Non-Sparse Coding
We propose an interpretable deep structure namely Frank-Wolfe Network (F-W Net), whose architecture is inspired by unrolling and truncating the Frank-Wolfe algorithm for solving an $L_p$-norm constrained problem with $p\geq 1$.
Dense 3-D Mapping with Spatial Correlation via Gaussian Filtering
Many accurate and efficient methods exist that address this problem but most assume that the occupancy states of different elements in the map representation are statistically independent.
Robotics
Fast, Autonomous Flight in GPS-Denied and Cluttered Environments
One of the most challenging tasks for a flying robot is to autonomously navigate between target locations quickly and reliably while avoiding obstacles in its path, and with little to no a-priori knowledge of the operating environment.
Robotics
Robust Stereo Visual Inertial Odometry for Fast Autonomous Flight
However, we still encounter challenges in terms of improving the computational efficiency and robustness of the underlying algorithms for applications in autonomous flight with micro aerial vehicles in which it is difficult to use high quality sensors and pow- erful processors because of constraints on size and weight.
Robotics
Human Pose Estimation using Global and Local Normalization
We present a two-stage normalization scheme, human body normalization and limb normalization, to make the distribution of the relative joint locations compact, resulting in easier learning of convolutional spatial models and more accurate pose estimation.
Relative Fisher Information and Natural Gradient for Learning Large Modular Models
Fisher information and natural gradient provided deep insights and powerful tools to artificial neural networks.
Clustering in Hilbert simplex geometry
In the Hilbert simplex geometry, the distance is the non-separable Hilbert's metric distance which satisfies the property of information monotonicity with distance level set functions described by polytope boundaries.
Coarse Grained Exponential Variational Autoencoders
Variational autoencoders (VAE) often use Gaussian or category distribution to model the inference process.
On Hölder projective divergences
We describe a framework to build distances by measuring the tightness of inequalities, and introduce the notion of proper statistical divergences and improper pseudo-divergences.
Deep Feature Consistent Variational Autoencoder
We present a novel method for constructing Variational Autoencoder (VAE).
Automatic Visual Theme Discovery from Joint Image and Text Corpora
Furthermore, not all tags have the same descriptive power for visual contents and large vocabulary available from natural language could result in a very diverse set of keywords.
Object Specific Deep Learning Feature and Its Application to Face Detection
We present a method for discovering and exploiting object specific deep learning features and use face detection as a case study.
Relative Natural Gradient for Learning Large Complex Models
Fisher information and natural gradient provided deep insights and powerful tools to artificial neural networks.
Guaranteed bounds on the Kullback-Leibler divergence of univariate mixtures using piecewise log-sum-exp inequalities
Information-theoretic measures such as the entropy, cross-entropy and the Kullback-Leibler divergence between two mixture models is a core primitive in many signal processing tasks.
Space-Time Local Embeddings
We give theoretical propositions to show that space-time is a more powerful representation than Euclidean space.
Two-Stage Metric Learning
This induces in the input data space a new family of distance metric with unique properties.
