首页/论文/1905.03493

arXiv 1905.034932019-05-09cs.LGcs.AIcs.ITmath.ITstat.ML

Limits of Deepfake Detection: A Robust Estimation Viewpoint

University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

Sakshi Agarwal, Lav R. Varshney

英文摘要：

Deepfake detection is formulated as a hypothesis testing problem to classify an image as genuine or GAN-generated. A robust statistics view of GANs is considered to bound the error probability for various GAN implementations in terms of their performance. The bounds are further simplified using a Euclidean approximation for the low error regime. Lastly, relationships between error probability and epidemic thresholds for spreading processes in networks are established.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders

University of Trento（特伦托大学）

Human Pose Estimation (HPE) aims at retrieving the 3D position of human joints from images or videos. We show that current 3D HPE methods suffer a lack of viewpoint equivariance, namely they tend to fail or perform poorly when dealing with viewpoints unseen at training time. Deep learning methods often rely on either scale-invariant, translation-invariant, or rotation-invariant operations, such as max-pooling. However, the adoption of such procedures does not necessarily improve viewpoint generalization, rather leading to more data-dependent methods. To tackle this issue, we propose a novel ca…

2021-08-19cs.CVcs.LG

Self-supervised 3D Shape and Viewpoint Estimation from Single Images for Robotics

University of Freiburg（弗莱堡大学）；Toyota Research Institute（丰田研究院）

We present a convolutional neural network for joint 3D shape prediction and viewpoint estimation from a single input image. During training, our network gets the learning signal from a silhouette of an object in the input image - a form of self-supervision. It does not require ground truth data for 3D shapes and the viewpoints. Because it relies on such a weak form of supervision, our approach can easily be applied to real-world data. We demonstrate that our method produces reasonable qualitative and quantitative results on natural images for both shape estimation and viewpoint prediction. Unl…

2019-10-17cs.CVcs.LGcs.RO

Crafting a multi-task CNN for viewpoint estimation

Convolutional Neural Networks (CNNs) were recently shown to provide state-of-the-art results for object category viewpoint estimation. However different ways of formulating this problem have been proposed and the competing approaches have been explored with very different design choices. This paper presents a comparison of these approaches in a unified setting as well as a detailed analysis of the key factors that impact performance. Followingly, we present a new joint training method with the detection task and demonstrate its benefit. We also highlight the superiority of classification appro…

2016-09-13cs.CVcs.LGcs.NE

Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres

University of Amsterdam（阿姆斯特丹大学）

Many computer vision challenges require continuous outputs, but tend to be solved by discrete classification. The reason is classification's natural containment within a probability $n$-simplex, as defined by the popular softmax activation function. Regular regression lacks such a closed geometry, leading to unstable training and convergence to suboptimal local minima. Starting from this insight we revisit regression in convolutional neural networks. We observe many continuous output problems in computer vision are naturally contained in closed geometrical manifolds, like the Euler angles in v…

2019-04-10cs.CVcs.LG

Perceptual Loss for Robust Unsupervised Homography Estimation

NavInfo Europe（四维图新欧洲）

Homography estimation is often an indispensable step in many computer vision tasks. The existing approaches, however, are not robust to illumination and/or larger viewpoint changes. In this paper, we propose bidirectional implicit Homography Estimation (biHomE) loss for unsupervised homography estimation. biHomE minimizes the distance in the feature space between the warped image from the source viewpoint and the corresponding image from the target viewpoint. Since we use a fixed pre-trained feature extractor and the only learnable component of our framework is the homography network, we effec…

2021-04-20cs.AIcs.CVcs.LG

BVE + EKF：一种利用扩展卡尔曼滤波器估计物体在3D任务空间中位置的视点估计器

BVE + EKF: A viewpoint estimator for the estimation of the object's position in the 3D task space using Extended Kalman Filters

INESC TEC；FEUP（波尔图工程学院）；ISR, University of Coimbra（科英布拉大学系统与机器人研究所）；KUCARS, Khalifa University（哈利法大学 KUCARS）

针对RGB-D传感器易受环境干扰及深度学习方案复杂难预测的问题，提出由EKF驱动的高斯视点估计器BVE预测物体3D位置，实验平均欧几里得误差约32 mm。

2024-10-03cs.LGcs.ROcs.SY

更多相关论文收起更多论文

Next-Best-View Estimation based on Deep Reinforcement Learning for Active Object Classification

University of Koblenz（科布伦茨大学）；York University（约克大学）

The presentation and analysis of image data from a single viewpoint are often not sufficient to solve a task. Several viewpoints are necessary to obtain more information. The next-best-view problem attempts to find the optimal viewpoint with the greatest information gain for the underlying task. In this work, a robot arm holds an object in its end-effector and searches for a sequence of next-best-view to explicitly identify the object. We use Soft Actor-Critic (SAC), a method of deep reinforcement learning, to learn these next-best-views for a specific set of objects. The evaluation shows that…

2021-10-14cs.LGcs.RO

Monocular Depth Estimation with Directional Consistency by Deep Networks

University of Applied Sciences Munich（慕尼黑应用科学大学）

As processing power has become more available, more human-like artificial intelligences are created to solve image processing tasks that we are inherently good at. As such we propose a model that estimates depth from a monocular image. Our approach utilizes a combination of structure from motion and stereo disparity. We estimate a pose between the source image and a different viewpoint and a dense depth map and use a simple transformation to reconstruct the image seen from said viewpoint. We can then use the real image at that viewpoint to act as supervision to train out model. The metric chos…

2019-05-11cs.CVcs.LG

Robust Generalized Method of Moments: A Finite Sample Viewpoint

MIT（麻省理工学院）；Microsoft Research, New England（微软研究院新英格兰分部）

For many inference problems in statistics and econometrics, the unknown parameter is identified by a set of moment conditions. A generic method of solving moment conditions is the Generalized Method of Moments (GMM). However, classical GMM estimation is potentially very sensitive to outliers. Robustified GMM estimators have been developed in the past, but suffer from several drawbacks: computational intractability, poor dimension-dependence, and no quantitative recovery guarantees in the presence of a constant fraction of outliers. In this work, we develop the first computationally efficient G…

2021-10-13cs.DScs.LGecon.EM

基于效用的短缺风险优化：非渐近视角

Optimization of utility-based shortfall risk: A non-asymptotic viewpoint

本文研究金融风险度量UBSR的估计与优化，推导了样本平均近似的非渐近误差界，提出渐近无偏的梯度估计器，并将其纳入随机梯度算法，给出收敛速率的非渐近界。

2024-03-30cs.LG

Convolutional Neural Networks for joint object detection and pose estimation: A comparative study

Université Paris-Est（巴黎东大）

In this paper we study the application of convolutional neural networks for jointly detecting objects depicted in still images and estimating their 3D pose. We identify different feature representations of oriented objects, and energies that lead a network to learn this representations. The choice of the representation is crucial since the pose of an object has a natural, continuous structure while its category is a discrete variable. We evaluate the different approaches on the joint object detection and pose estimation task of the Pascal3D+ benchmark using Average Viewpoint Precision. We show…

2015-02-28cs.CVcs.LGcs.NE

面向离策略强化学习的基于平滑泛函的梯度算法：非渐近视角

Smoothed functional-based gradient algorithms for off-policy reinforcement learning: A non-asymptotic viewpoint

Indian Institute of Technology Madras（马德拉斯印度理工学院）

针对离策略强化学习控制问题，提出两种基于平滑泛函梯度估计的策略梯度算法，推导其非渐近收敛界，证实带方差缩减的第二种算法收敛速率更优。

2024-06-23cs.LG

Self-Supervised 3D Keypoint Learning for Ego-motion Estimation

Toyota Research Institute（丰田研究院）；KTH Royal Institute of Technology（瑞典皇家理工学院）

Detecting and matching robust viewpoint-invariant keypoints is critical for visual SLAM and Structure-from-Motion. State-of-the-art learning-based methods generate training samples via homography adaptation to create 2D synthetic views with known keypoint matches from a single image. This approach, however, does not generalize to non-planar 3D scenes with illumination variations commonly seen in real-world videos. In this work, we propose self-supervised learning of depth-aware keypoints directly from unlabeled videos. We jointly learn keypoint and depth estimation networks by combining appear…

2020-11-18cs.CVcs.LGcs.RO