research
∙
10/30/2022
A simple, efficient and scalable contrastive masked autoencoder for learning visual representations
We introduce CAN, a simple, efficient and scalable method for self-super...
share
research
∙
04/19/2022
Poisons that are learned faster are more effective
Imperceptible poisoning attacks on entire datasets have recently been to...
research
∙
04/07/2022
Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer
Videos are created to express emotion, exchange information, and share e...
research
∙
03/17/2022
On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels
We study the properties of various over-parametrized convolutional neura...
research
∙
12/01/2021
Object-Aware Cropping for Self-Supervised Learning
A core component of the recent success of self-supervised learning is cr...
research
∙
10/27/2021
Robust Contrastive Learning Using Negative Samples with Diminished Semantics
Unsupervised learning has recently made exceptional progress because of ...
research
∙
08/25/2021
Maneuver Identification Challenge
AI algorithms that identify maneuvers from trajectory data could play an...
research
∙
03/22/2021
Improved Detection of Face Presentation Attacks Using Image Decomposition
Presentation attack detection (PAD) is a critical component in secure fa...
research
∙
03/03/2021
Shift Invariance Can Reduce Adversarial Robustness
Shift invariance is a critical property of CNNs that improves performanc...
research
∙
02/15/2021
Low Curvature Activations Reduce Overfitting in Adversarial Training
Adversarial training is one of the most effective defenses against adver...
research
∙
11/03/2020
Learning Visual Representations for Transfer Learning by Suppressing Texture
Recent literature has shown that features obtained from supervised train...
research
∙
07/03/2020
On the Similarity between the Laplace and Neural Tangent Kernels
Recent theoretical work has shown that massively overparameterized neura...
research
∙
06/07/2020
SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation
We propose a novel method for combining synthetic and real images when t...
research
∙
04/10/2020
Towards Automatic Generation of Questions from Long Answers
Automatic question generation (AQG) has broad applicability in domains s...
research
∙
03/10/2020
Frequency Bias in Neural Networks for Input of Non-Uniform Density
Recent works have partly attributed the generalization ability of over-p...
research
∙
06/02/2019
The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies
We study the relationship between the speed at which a neural network le...
research
∙
05/20/2019
Adversarially robust transfer learning
Transfer learning, in which a network is trained on one task and re-purp...
research
∙
01/06/2019
Understanding the (un)interpretability of natural image distributions using generative models
Probability density estimation is a classical and well studied problem, ...
research
∙
12/02/2017
SfSNet : Learning Shape, Reflectance and Illuminance of Faces in the Wild
We present SfSNet, an end-to-end learning framework for producing an acc...
research
∙
05/20/2017
Stabilizing Adversarial Nets With Prediction Methods
Adversarial neural networks solve many important problems in data scienc...
research
∙
11/23/2016
3D Menagerie: Modeling the 3D shape and pose of animals
There has been significant work on learning realistic, articulated, 3D m...
research
∙
10/18/2016
Big Batch SGD: Automated Inference using Adaptive Batch Sizes
Classical stochastic gradient methods for optimization rely on noisy gra...
research
∙
05/31/2016
Biconvex Relaxation for Semidefinite Programming in Computer Vision
Semidefinite programming is an indispensable tool in computer vision, bu...
research
∙
02/15/2016
Efficient Representation of Low-Dimensional Manifolds using Deep Networks
We consider the ability of deep neural networks to represent data that l...
research
∙
07/28/2015
A Hyperelastic Two-Scale Optimization Model for Shape Matching
We suggest a novel shape matching algorithm for three-dimensional surfac...
research
∙
12/16/2014
Locally Scale-Invariant Convolutional Neural Networks
Convolutional Neural Networks (ConvNets) have shown excellent results on...
research
∙
05/05/2014