Based on this single-image-annotation experiment, we design an experiment to quickly annotate an entire data set.
Anomaly detection is a well-established research area that seeks to identify samples outside of a predetermined distribution.
Ranked #1 on Anomaly Detection on One-class CIFAR-100 (using extra training data)
In addition, we validated our adversarial mask effectiveness in real-world experiments by printing the adversarial pattern on a fabric medical face mask, causing the FR system to identify only 3. 34% of the participants wearing the mask (compared to a minimum of 83. 34% with other evaluated masks).
We present a new method for real-time non-rigid dense correspondence between point clouds based on structured shape construction.
Ranked #1 on 3D Dense Shape Correspondence on SHREC'19
To use kNet, we first train a preliminary network on the data set, and then train kNet on the penultimate layer of the preliminary network. We find that kNet gives a smooth approximation of kNN, and cannot handle the sharp label changes between samples that kNN can exhibit.
Experiments on several datasets reveal that we can cut the number of ReLU operations by up to three orders of magnitude and, as a result, cut the communication bandwidth by more than 50%.
Additionally, we demonstrate the robustness of our attack in the case of defense, where we show that remnant characteristics of the target shape are still present at the output after applying the defense to the adversarial input.
The search for efficient neural network architectures has gained much focus in recent years, where modern architectures focus not only on accuracy but also on inference time and model size.
As image generation techniques mature, there is a growing interest in explainable representations that are easy to understand and intuitive to manipulate.
We show that the proposed approximation is superior to the commonly used spectral methods with respect to both accuracy and complexity.
We base our algorithm on the assumption that the image available to the encoder and the image available to the decoder are correlated, and we let the network learn these correlations in the training phase.
The field of self-supervised monocular depth estimation has seen huge advancements in recent years.
Ranked #26 on Monocular Depth Estimation on KITTI Eigen split
We consider the problem of segmenting dynamic regions in CrowdCam images, where a dynamic region is the projection of a moving 3D object on the image plane.
The attenuation depends both on the water body and the 3D structure of the scene, making color restoration difficult.
We investigate the classification performance of K-nearest neighbors (K-NN) and deep neural networks (DNNs) in the presence of label noise.
We propose a novel method for template matching in unconstrained environments.
We demonstrate on real-world data that our algorithm is capable of completing a full 3D scene from a single depth image and can synthesize a full depth map from a novel viewpoint of the scene.
This work presents a novel approach for detecting inliers in a given set of correspondences (matches).
Instead of having both cameras send their entire image to the host computer, the left camera sends its image to the host while the right camera sends only a fraction $\epsilon$ of its image.
Fast-Match is a fast algorithm for approximate template matching under 2D affine transformations that minimizes the Sum-of-Absolute-Differences (SAD) error measure.