Search Results for author: Arash Vahdat

Found 24 papers, 9 papers with code

HANT: Hardware-Aware Network Transformation

no code implementations12 Jul 2021 Pavlo Molchanov, Jimmy Hall, Hongxu Yin, Jan Kautz, Nicolo Fusi, Arash Vahdat

HANT tackles the problem in two phase: In the first phase, a large number of alternative operations per every layer of the teacher model is trained using layer-wise feature map distillation.

Neural Architecture Search Quantization

Score-based Generative Modeling in Latent Space

no code implementations10 Jun 2021 Arash Vahdat, Karsten Kreis, Jan Kautz

Moving from data to latent space allows us to train more expressive generative models, apply SGMs to non-continuous data, and learn smoother SGMs in a smaller space, resulting in fewer network evaluations and faster sampling.

Image Generation

Multi-task Transformation Learning for Robust Out-of-Distribution Detection

no code implementations7 Jun 2021 Sina Mohseni, Arash Vahdat, Jay Yadawa

Detecting out-of-distribution (OOD) samples plays a key role in open-world and safety-critical applications such as autonomous systems and healthcare.

Anomaly Detection Contrastive Learning +2

See through Gradients: Image Batch Recovery via GradInversion

no code implementations CVPR 2021 Hongxu Yin, Arun Mallya, Arash Vahdat, Jose M. Alvarez, Jan Kautz, Pavlo Molchanov

In this work, we introduce GradInversion, using which input images from a larger batch (8 - 48 images) can also be recovered for large networks such as ResNets (50 layers), on complex datasets such as ImageNet (1000 classes, 224x224 px).

Federated Learning Inference Attack

NCP-VAE: Variational Autoencoders with Noise Contrastive Priors

no code implementations6 Oct 2020 Jyoti Aneja, Alexander Schwing, Jan Kautz, Arash Vahdat

To tackle this issue, we propose an energy-based prior defined by the product of a base prior distribution and a reweighting factor, designed to bring the base closer to the aggregate posterior.

Ranked #2 on Image Generation on CelebA 256x256 (FID metric)

Image Generation

VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models

no code implementations ICLR 2021 Zhisheng Xiao, Karsten Kreis, Jan Kautz, Arash Vahdat

VAEBM captures the overall mode structure of the data distribution using a state-of-the-art VAE and it relies on its EBM component to explicitly exclude non-data-like regions from the model and refine the image samples.

Image Generation Out-of-Distribution Detection

NVAE: A Deep Hierarchical Variational Autoencoder

4 code implementations NeurIPS 2020 Arash Vahdat, Jan Kautz

For example, on CIFAR-10, NVAE pushes the state-of-the-art from 2. 98 to 2. 91 bits per dimension, and it produces high-quality images on CelebA HQ.

Ranked #2 on Image Generation on FFHQ 256 x 256 (bits/dimension metric)

Image Generation

Contrastive Learning for Weakly Supervised Phrase Grounding

1 code implementation ECCV 2020 Tanmay Gupta, Arash Vahdat, Gal Chechik, Xiaodong Yang, Jan Kautz, Derek Hoiem

Given pairs of images and captions, we maximize compatibility of the attention-weighted regions and the words in the corresponding caption, compared to non-corresponding pairs of images and captions.

Contrastive Learning Language Modelling +1

On the distance between two neural networks and the stability of learning

1 code implementation NeurIPS 2020 Jeremy Bernstein, Arash Vahdat, Yisong Yue, Ming-Yu Liu

This paper relates parameter distance to gradient breakdown for a broad class of nonlinear compositional functions.

UNAS: Differentiable Architecture Search Meets Reinforcement Learning

1 code implementation CVPR 2020 Arash Vahdat, Arun Mallya, Ming-Yu Liu, Jan Kautz

Our framework brings the best of both worlds, and it enables us to search for architectures with both differentiable and non-differentiable criteria in one unified framework while maintaining a low search cost.

Neural Architecture Search

A Robust Learning Approach to Domain Adaptive Object Detection

1 code implementation ICCV 2019 Mehran Khodabandeh, Arash Vahdat, Mani Ranjbar, William G. Macready

To adapt to the domain shift, the model is trained on the target domain using a set of noisy object bounding boxes that are obtained by a detection model trained only in the source domain.

Domain Adaptation Robust Object Detection +1

Improved Gradient-Based Optimization Over Discrete Distributions

no code implementations29 Sep 2018 Evgeny Andriyash, Arash Vahdat, Bill Macready

In many applications we seek to maximize an expectation with respect to a distribution over discrete variables.

Variational Inference

DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors

no code implementations NeurIPS 2018 Arash Vahdat, Evgeny Andriyash, William G. Macready

Experiments on the MNIST and OMNIGLOT datasets show that these relaxations outperform previous discrete VAEs with Boltzmann priors.

DVAE++: Discrete Variational Autoencoders with Overlapping Transformations

no code implementations ICML 2018 Arash Vahdat, William G. Macready, Zhengbing Bian, Amir Khoshaman, Evgeny Andriyash

Training of discrete latent variable models remains challenging because passing gradient information through discrete units is difficult.

Ranked #36 on Image Generation on CIFAR-10 (bits/dimension metric)

Image Generation Latent Variable Models

Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks

1 code implementation NeurIPS 2017 Arash Vahdat

Collecting large training datasets, annotated with high-quality labels, is costly and time-consuming.

Hierarchical Deep Temporal Models for Group Activity Recognition

1 code implementation9 Jul 2016 Mostafa S. Ibrahim, Srikanth Muralidharan, Zhiwei Deng, Arash Vahdat, Greg Mori

In order to model both person-level and group-level dynamics, we present a 2-stage deep temporal model for the group activity recognition problem.

Group Activity Recognition

A Hierarchical Deep Temporal Model for Group Activity Recognition

1 code implementation CVPR 2016 Moustafa Ibrahim, Srikanth Muralidharan, Zhiwei Deng, Arash Vahdat, Greg Mori

In group activity recognition, the temporal dynamics of the whole activity can be inferred based on the dynamics of the individual people representing the activity.

Group Activity Recognition

Latent Maximum Margin Clustering

no code implementations NeurIPS 2013 Guang-Tong Zhou, Tian Lan, Arash Vahdat, Greg Mori

We present a maximum margin framework that clusters data using latent variables.

Kernel Latent SVM for Visual Recognition

no code implementations NeurIPS 2012 Weilong Yang, Yang Wang, Arash Vahdat, Greg Mori

Latent SVMs (LSVMs) are a class of powerful tools that have been successfully applied to many applications in computer vision.

Cannot find the paper you are looking for? You can Submit a new open access paper.