Search Results for author:
Found 42 papers, 12 papers with code
Deep Learning Meets Satellite Images -- An Evaluation on Handcrafted and Learning-based Features for Multi-date Satellite Stereo Images
A critical step in the digital surface models(DSM) generation is feature matching.
A General Albedo Recovery Approach for Aerial Photogrammetric Images through Inverse Rendering
Modeling outdoor scenes for the synthetic 3D environment requires the recovery of reflectance/albedo information from raw images, which is an ill-posed problem due to the complicated unmodeled physics in this process (e. g., indirect lighting, volume scattering, specular reflection).
EAR: Edge-Aware Reconstruction of 3-D vertebrae structures from bi-planar X-ray images
However, due to the projection process of X-ray imaging, much spatial information has been lost.
Multi-view X-ray Image Synthesis with Multiple Domain Disentanglement from CT Scans
Meanwhile, we also impose a supervised process by computing the similarity of computed real DRR and synthesized DRR images.
Scalable Scene Modeling from Perspective Imaging: Physics-based Appearance and Geometry Inference
3D scene modeling techniques serve as the bedrocks in the geospatial engineering and computer science, which drives many applications ranging from automated driving, terrain mapping, navigation, virtual, augmented, mixed, and extended reality (for gaming and movie industry etc.).
Perceptual learning in contour detection transfer across changes in contour path and orientation
The integration of local elements into shape contours is critical for target detection and identification in cluttered scenes.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
In this report, we introduce the Gemini 1. 5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio.
Private Learning with Public Features
We study a class of private learning problems in which the data is a join of private and public features.
Feature Proliferation -- the "Cancer" in StyleGAN and its Treatments
Thanks to our discovery of Feature Proliferation, the proposed feature rescaling method is less destructive and retains more useful image features than the truncation trick, as it is more fine-grained and works in a lower-level feature space rather than a high-level latent space.
Mesh Conflation of Oblique Photogrammetric Models using Virtual Cameras and Truncated Signed Distance Field
Conflating/stitching 2. 5D raster digital surface models (DSM) into a large one has been a running practice in geoscience applications, however, conflating full-3D mesh models, such as those from oblique photogrammetry, is extremely challenging.
Multi-Task Differential Privacy Under Distribution Skew
We study the problem of multi-task learning under user-level differential privacy, in which $n$ users contribute data to $m$ tasks, each involving a subset of users.
Point Cloud Registration for LiDAR and Photogrammetric Data: a Critical Synthesis and Performance Analysis on Classic and Deep Learning Algorithms
In this work, we provide a comprehensive review of the state-of-the-art (SOTA) point cloud registration methods, where we analyze and evaluate these methods using a diverse set of point cloud data from indoor to satellite sources.
Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints
Specifically, we demonstrate that training over aggregates can provide significant gains in prediction accuracy over the existing state-of-the-art for StackOverflow, CIFAR10 and CIFAR100 datasets.
Measuring Forgetting of Memorized Training Examples
In memorization, models overfit specific training examples and become susceptible to privacy attacks.
A Novel Intrinsic Image Decomposition Method to Recover Albedo for Aerial Images in Photogrammetry Processing
Recovering surface albedos from photogrammetric images for realistic rendering and synthetic environments can greatly facilitate its downstream applications in VR/AR/MR and digital twins.
Debugging Differential Privacy: A Case Study for Privacy Auditing
Differential Privacy can provide provable privacy guarantees for training data in machine learning.
Toward Training at ImageNet Scale with Differential Privacy
Despite a rich literature on how to train ML models with differential privacy, it remains extremely challenging to train real-life, large neural networks with both reasonable accuracy and privacy.
Membership Inference Attacks From First Principles
A membership inference attack allows an adversary to query a trained machine learning model to predict whether or not a particular example was contained in the model's training dataset.
ViF-SD2E: A Robust Weakly-Supervised Method for Neural Decoding
Neural decoding plays a vital role in the interaction between the brain and the outside world.
Differentially Private Model Personalization
We study personalization of supervised learning with user-level differential privacy.
Public Data-Assisted Mirror Descent for Private Model Training
In this paper, we revisit the problem of using in-distribution public data to improve the privacy/utility trade-offs for differentially private (DP) model training.
Vis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Learned Virtual View Visibility
Then the visibility information of multiple views is aggregated to generate a 3D mesh model by solving an optimization problem considering visibility in which a novel adaptive visibility weighting in surface determination is also introduced to suppress line of sight with a large incident angle.
A volumetric change detection framework using UAV oblique photogrammetry - A case study of ultra-high-resolution monitoring of progressive building collapse
In this paper, we present a case study that performs an unmanned aerial vehicle (UAV) based fine-scale 3D change detection and monitoring of progressive collapse performance of a building during a demolition event.
Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates
We study the problem of differentially private (DP) matrix completion under user-level privacy.
3D Reconstruction through Fusion of Cross-View Images
3D recovery from multi-stereo and stereo images, as an important application of the image-based perspective geometry, serves many applications in computer vision, remote sensing and Geomatics.
Practical and Private (Deep) Learning without Sampling or Shuffling
We consider training models with differential privacy (DP) using mini-batch gradients.
Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning
DP formalizes this data leakage through a cryptographic game, where an adversary must predict if a model was trained on a dataset D, or a dataset D' that differs in just one example. If observing the training algorithm does not meaningfully increase the adversary's odds of successfully guessing which dataset the model was trained on, then the algorithm is said to be differentially private.
The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space
We propose an $(\epsilon,\delta)$-differentially private algorithm that approximates $\dist$ within a factor of $(1\pm\gamma)$, and with additive error of $O(\sqrt{\ln(1/\delta)}/\epsilon)$, using space $O(\ln(\ln(u)/\gamma)/\gamma^2)$.
Is Private Learning Possible with Instance Encoding?
A private machine learning algorithm hides as much as possible about its training data while still preserving accuracy.
Tempered Sigmoid Activations for Deep Learning with Differential Privacy
Because learning sometimes involves sensitive data, machine learning algorithms have been extended to offer privacy for training data.
Evading Curse of Dimensionality in Unconstrained Private GLMs via Private Gradient Descent
We show that for unconstrained convex generalized linear models (GLMs), one can obtain an excess empirical risk of $\tilde O\left(\sqrt{{\texttt{rank}}}/\epsilon n\right)$, where ${\texttt{rank}}$ is the rank of the feature matrix in the GLM problem, $n$ is the number of data samples, and $\epsilon$ is the privacy parameter.
Combining MixMatch and Active Learning for Better Accuracy with Fewer Labels
This analysis can be used to measure the relative value of labeled/unlabeled data at different points of the learning curve, where we find that although the incremental value of labeled data can be as much as 20x that of unlabeled, it quickly diminishes to less than 3x once more than 2, 000 labeled example are observed.
Making the Shoe Fit: Architectures, Initializations, and Tuning for Learning with Privacy
Because learning sometimes involves sensitive data, standard machine-learning algorithms have been extended to offer strong privacy guarantees for training data.
That which we call private
Instead, the definitions so named are the basis of refinements and more advanced analyses of the worst-case implications of attackers---without any change assumed in attackers' powers.
A Comparison of Stereo-Matching Cost between Convolutional Neural Network and Census for Satellite Images
Stereo dense image matching can be categorized to low-level feature based matching and deep feature based matching according to their matching cost metrics.
Renyi Differential Privacy Mechanisms for Posterior Sampling
With the newly proposed privacy definition of Rényi Differential Privacy (RDP) in (Mironov, 2017), we re-examine the inherent privacy of releasing a single sample from a posterior distribution.
Rényi Differential Privacy Mechanisms for Posterior Sampling
Using a recently proposed privacy definition of R\'enyi Differential Privacy (RDP), we re-examine the inherent privacy of releasing a single sample from a posterior distribution.
Composition Properties of Inferential Privacy for Time-Series Data
With the proliferation of mobile devices and the internet of things, developing principled solutions for privacy in time series applications has become increasingly important.
Pufferfish Privacy Mechanisms for Correlated Data
Since this mechanism may be computationally inefficient, we provide an additional mechanism that applies to some practical cases such as physical activity measurements across time, and is computationally efficient.
Learning from Data with Heterogeneous Noise using SGD
In this paper, we adopt instead a model in which data is observed through heterogeneous noise, where the noise level reflects the quality of the data source.
The Large Margin Mechanism for Differentially Private Maximization
A basic problem in the design of privacy-preserving algorithms is the private maximization problem: the goal is to pick an item from a universe that (approximately) maximizes a data-dependent function, all under the constraint of differential privacy.
