Search Results for author:
Found 43 papers, 11 papers with code
Learning to Control under Time-Varying Environment
To the best of our knowledge, our study establishes the first model-based online algorithm with regret guarantees under LTV dynamical systems.
Exposing Fine-grained Adversarial Vulnerability of Face Anti-spoofing Models
Adversarial attacks seriously threaten the high accuracy of face anti-spoofing models.
Can We Do Better Than Random Start? The Power of Data Outsourcing
Based on three different scenarios, we propose simulation-based algorithms that can utilize a small amount of outsourced data to find good initial points accordingly.
Algorithms and Theory for Supervised Gradual Domain Adaptation
We thus study the problem of supervised gradual domain adaptation, where labeled data from shifting distributions are available to the learner along the trajectory, and we aim to learn a classifier on a target data distribution of interest.
iSDF: Real-Time Neural Signed Distance Fields for Robot Perception
We present iSDF, a continual learning system for real-time signed distance field (SDF) reconstruction.
Provably Efficient Convergence of Primal-Dual Actor-Critic with Nonlinear Function Approximation
We study the convergence of the actor-critic algorithm with nonlinear function approximation under a nonconvex-nonconcave primal-dual formulation.
Stochastic Gradient Descent with Dependent Data for Offline Reinforcement Learning
The policy evaluation algorithm is then combined with the policy iteration algorithm to learn the optimal policy.
Differentially Private Temporal Difference Learning with Stochastic Nonconvex-Strongly-Concave Optimization
Temporal difference (TD) learning is a widely used method to evaluate policies in reinforcement learning.
DRAN: Detailed Region-Adaptive Normalization for Conditional Image Synthesis
To evaluate the effectiveness and generalization ability of DRAN, we conduct a set of experiments on makeup transfer and semantic image synthesis.
Incentivizing an Unknown Crowd
Motivated by the common strategic activities in crowdsourcing labeling, we study the problem of sequential eliciting information without verification (EIWV) for workers with a heterogeneous and unknown crowd.
A Systematical Solution for Face De-identification
Through this, we can construct unrestricted adversarial image to decrease ID similarity recognized by model.
DFGC 2021: A DeepFake Game Competition
This competition provides a common platform for benchmarking the adversarial game between current state-of-the-art DeepFake creation and detection methods.
Transferable Sparse Adversarial Attack
The experiment shows that our method has improved the transferability by a large margin under a similar sparsity setting compared with state-of-the-art methods.
Cascading Bandit under Differential Privacy
This paper studies \emph{differential privacy (DP)} and \emph{local differential privacy (LDP)} in cascading bandits.
CFA-Net: Controllable Face Anonymization Network with Identity Representation Manipulation
We propose a Controllable Face Anonymization Network (CFA-Net), a novel approach that can anonymize the identity of given faces in images and videos, based on a generator that can disentangle face identity from other image contents.
Robust Face-Swap Detection Based on 3D Facial Shape Information
Maliciously-manipulated images or videos - so-called deep fakes - especially face-swap images and videos have attracted more and more malicious attackers to discredit some key figures.
SOGAN: 3D-Aware Shadow and Occlusion Robust GAN for Makeup Transfer
Since human faces are symmetrical in the UV space, we can conveniently remove the undesired shadow and occlusion from the reference image by carefully designing a Flip Attention Module (FAM).
Combinatorial Bandits under Strategic Manipulations
Strategic behavior against sequential learning methods, such as "click framing" in real recommendation systems, have been widely observed.
On the SRPT Scheduling Discipline in Many-Server Queues with Impatient Customers
The shortest-remaining-processing-time (SRPT) scheduling policy has been extensively studied, for more than 50 years, in single-server queues with infinitely patient jobs.
Probability 60K25, 68M20, 90B22
A Primal-Dual Approach to Constrained Markov Decision Processes
In many operations management problems, we need to make decisions sequentially to minimize the cost while satisfying certain constraints.
Optimization and Control
Exploring Adversarial Fake Images on Face Manifold
Then, the generated fake images driven by the adversarial latent vectors with the help of GANs can defeat main-stream forensic models.
Distributed Thompson Sampling
To further improve the performance of distributed Thompson Sampling, we propose a distributed Elimination based Thompson Sampling algorithm that allow the agents to learn collaboratively.
MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation
To deal with this problem, we propose a novel multi-level statistics transfer model, which disentangles and transfers multi-level appearance features from person images and merges them with pose features to reconstruct the source person images themselves.
TLIO: Tight Learned Inertial Odometry
We show that our network, trained with pedestrian data from a headset, can produce statistically consistent measurement and uncertainty to be used as the update step in the filter, and the tightly-coupled system outperforms velocity integration approaches in position estimates, and AHRS attitude filter in orientation estimates.
Accelerating Nonconvex Learning via Replica Exchange Langevin Diffusion
To attain the advantages of both regimes, we propose to use replica exchange, which swaps between two Langevin diffusions with different temperatures.
Learning Pose-invariant 3D Object Reconstruction from Single-view Images
Learning to reconstruct 3D shapes using 2D images is an active research topic, with benefits of not requiring expensive 3D data.
Temporal Sparse Adversarial Attack on Sequence-based Gait Recognition
In this paper, we demonstrate that the state-of-the-art gait recognition model is vulnerable to such attacks.
Replica Exchange for Non-Convex Optimization
Gradient descent (GD) is known to converge quickly for convex objective functions, but it can be trapped at local minima.
A New Ensemble Method for Concessively Targeted Multi-model Attack
Thus, in this paper, we propose a new attack mechanism which performs the non-targeted attack when the targeted attack fails.
Scalable Fine-grained Generated Image Classification Based on Deep Metric Learning
The new types of generated images are emerging one after another, and the existing detection methods cannot cope well.
AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization
The point process is a solid framework to model sequential data, such as videos, by exploring the underlying relevance.
On Constructing Confidence Region for Model Parameters in Stochastic Gradient Descent via Batch Means
In this paper, we study a simple algorithm to construct asymptotically valid confidence regions for model parameters using the batch means method.
Efficient Inference and Exploration for Reinforcement Learning
Despite an ever growing literature on reinforcement learning algorithms and applications, much less is known about their statistical inference.
miniSAM: A Flexible Factor Graph Non-linear Least Squares Optimization Framework
Many problems in computer vision and robotics can be phrased as non-linear least squares optimization problems represented by factor graphs, for example, simultaneous localization and mapping (SLAM), structure from motion (SfM), motion planning, and control.
On the generalization of GAN image forensics
Recently the GAN generated face images are more and more realistic with high-quality, even hard for human eyes to detect.
Learning to Align Images using Weak Geometric Supervision
Such descriptors are often derived using supervised learning on existing datasets with ground truth correspondences.
Deep Steganalysis: End-to-End Learning with Supervisory Information beyond Class Labels
Recently, deep learning has shown its power in steganalysis.
DeepFirearm: Learning Discriminative Feature Representation for Fine-grained Firearm Retrieval
There are great demands for automatically regulating inappropriate appearance of shocking firearm images in social media or identifying firearm types in forensics.
Continuous-Time Gaussian Process Motion Planning via Probabilistic Inference
We benchmark our algorithms against several sampling-based and trajectory optimization-based motion planning algorithms on planning problems in multiple environments.
Robotics
SSGAN: Secure Steganography Based on Generative Adversarial Networks
Furthermore, a sophisticated steganalysis network is reconstructed for the discriminative network, and the network can better evaluate the performance of the generated images.
Sparse Gaussian Processes for Continuous-Time Trajectory Estimation on Matrix Lie Groups
Continuous-time trajectory representations are a powerful tool that can be used to address several issues in many practical simultaneous localization and mapping (SLAM) scenarios, like continuously collected measurements distorted by robot motion, or during with asynchronous sensor measurements.
Robotics
What Is the Best Practice for CNNs Applied to Visual Instance Retrieval?
Based on the evaluation results, we also identify the best choices for different factors and propose a new multi-scale image feature representation method to encode the image effectively.
4D Crop Monitoring: Spatio-Temporal Reconstruction for Agriculture
Autonomous crop monitoring at high spatial and temporal resolution is a critical problem in precision agriculture.
