To the best of our knowledge, our study establishes the first model-based online algorithm with regret guarantees under LTV dynamical systems.
Adversarial attacks seriously threaten the high accuracy of face anti-spoofing models.
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.
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.
We present iSDF, a continual learning system for real-time signed distance field (SDF) reconstruction.
We study the convergence of the actor-critic algorithm with nonlinear function approximation under a nonconvex-nonconcave primal-dual formulation.
The policy evaluation algorithm is then combined with the policy iteration algorithm to learn the optimal policy.
Temporal difference (TD) learning is a widely used method to evaluate policies in reinforcement learning.
To evaluate the effectiveness and generalization ability of DRAN, we conduct a set of experiments on makeup transfer and semantic image synthesis.
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.
1 code implementation • 2 Jun 2021 • Bo Peng, Hongxing Fan, Wei Wang, Jing Dong, Yuezun Li, Siwei Lyu, Qi Li, Zhenan Sun, Han Chen, Baoying Chen, Yanjie Hu, Shenghai Luo, Junrui Huang, Yutong Yao, Boyuan Liu, Hefei Ling, Guosheng Zhang, Zhiliang Xu, Changtao Miao, Changlei Lu, Shan He, Xiaoyan Wu, Wanyi Zhuang
This competition provides a common platform for benchmarking the adversarial game between current state-of-the-art DeepFake creation and detection methods.
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.
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.
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.
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).
Strategic behavior against sequential learning methods, such as "click framing" in real recommendation systems, have been widely observed.
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
In many operations management problems, we need to make decisions sequentially to minimize the cost while satisfying certain constraints.
Optimization and Control
Then, the generated fake images driven by the adversarial latent vectors with the help of GANs can defeat main-stream forensic models.
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.
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.
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.
To attain the advantages of both regimes, we propose to use replica exchange, which swaps between two Langevin diffusions with different temperatures.
Learning to reconstruct 3D shapes using 2D images is an active research topic, with benefits of not requiring expensive 3D data.
In this paper, we demonstrate that the state-of-the-art gait recognition model is vulnerable to such attacks.
Thus, in this paper, we propose a new attack mechanism which performs the non-targeted attack when the targeted attack fails.
The new types of generated images are emerging one after another, and the existing detection methods cannot cope well.
The point process is a solid framework to model sequential data, such as videos, by exploring the underlying relevance.
In this paper, we study a simple algorithm to construct asymptotically valid confidence regions for model parameters using the batch means method.
Despite an ever growing literature on reinforcement learning algorithms and applications, much less is known about their statistical inference.
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.
Recently the GAN generated face images are more and more realistic with high-quality, even hard for human eyes to detect.
Such descriptors are often derived using supervised learning on existing datasets with ground truth correspondences.
There are great demands for automatically regulating inappropriate appearance of shocking firearm images in social media or identifying firearm types in forensics.
We benchmark our algorithms against several sampling-based and trajectory optimization-based motion planning algorithms on planning problems in multiple environments.
Furthermore, a sophisticated steganalysis network is reconstructed for the discriminative network, and the network can better evaluate the performance of the generated images.
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.
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.
Autonomous crop monitoring at high spatial and temporal resolution is a critical problem in precision agriculture.