Search Results for author: Wojciech Czaja

Found 13 papers, 7 papers with code

Emergence of the SVD as an interpretable factorization in deep learning for inverse problems

1 code implementation18 Jan 2023 Shashank Sule, Richard G. Spencer, Wojciech Czaja

We demonstrate the emergence of weight matrix singular value decomposition (SVD) in interpreting neural networks (NNs) for parameter estimation from noisy signals.

Active Learning at the ImageNet Scale

1 code implementation25 Nov 2021 Zeyad Ali Sami Emam, Hong-Min Chu, Ping-Yeh Chiang, Wojciech Czaja, Richard Leapman, Micah Goldblum, Tom Goldstein

Active learning (AL) algorithms aim to identify an optimal subset of data for annotation, such that deep neural networks (DNN) can achieve better performance when trained on this labeled subset.

Active Learning

Protecting Proprietary Data: Poisoning for Secure Dataset Release

no code implementations29 Sep 2021 Liam H Fowl, Ping-Yeh Chiang, Micah Goldblum, Jonas Geiping, Arpit Amit Bansal, Wojciech Czaja, Tom Goldstein

These two behaviors can be in conflict as an organization wants to prevent competitors from using their own data to replicate the performance of their proprietary models.

Data Poisoning

Exploring the high dimensional geometry of HSI features

1 code implementation1 Mar 2021 Wojciech Czaja, Ilya Kavalerov, Weilin Li

We explore feature space geometries induced by the 3-D Fourier scattering transform and deep neural network with extended attribute profiles on four standard hyperspectral images.

Maximal function pooling with applications

no code implementations1 Mar 2021 Wojciech Czaja, Weilin Li, Yiran Li, Mike Pekala

Inspired by the Hardy-Littlewood maximal function, we propose a novel pooling strategy which is called maxfun pooling.

Image Classification

Cortical Features for Defense Against Adversarial Audio Attacks

1 code implementation30 Jan 2021 Ilya Kavalerov, Ruijie Zheng, Wojciech Czaja, Rama Chellappa

We propose using a computational model of the auditory cortex as a defense against adversarial attacks on audio.

A study of quality and diversity in K+1 GANs

no code implementations NeurIPS Workshop ICBINB 2020 Ilya Kavalerov, Wojciech Czaja, Rama Chellappa

We study the K+1 GAN paradigm which generalizes the canonical true/fake GAN by training a generator with a K+1-ary classifier instead of a binary discriminator.

Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching

1 code implementation ICLR 2021 Jonas Geiping, Liam Fowl, W. Ronny Huang, Wojciech Czaja, Gavin Taylor, Michael Moeller, Tom Goldstein

We consider a particularly malicious poisoning attack that is both "from scratch" and "clean label", meaning we analyze an attack that successfully works against new, randomly initialized models, and is nearly imperceptible to humans, all while perturbing only a small fraction of the training data.

Data Poisoning

cGANs with Multi-Hinge Loss

2 code implementations9 Dec 2019 Ilya Kavalerov, Wojciech Czaja, Rama Chellappa

We propose a new algorithm to incorporate class conditional information into the critic of GANs via a multi-class generalization of the commonly used Hinge loss that is compatible with both supervised and semi-supervised settings.

Conditional Image Generation

Transport Model for Feature Extraction

no code implementations31 Oct 2019 Wojciech Czaja, Dong Dong, Pierre-Emmanuel Jabin, Franck Olivier Ndjakou Njeunje

We present a new feature extraction method for complex and large datasets, based on the concept of transport operators on graphs.

Three-Dimensional Fourier Scattering Transform and Classification of Hyperspectral Images

2 code implementations17 Jun 2019 Ilya Kavalerov, Weilin Li, Wojciech Czaja, Rama Chellappa

Recent developments in machine learning and signal processing have resulted in many new techniques that are able to effectively capture the intrinsic yet complex properties of hyperspectral imagery.

Anomaly Detection Classification +3

Adversarial Examples in Remote Sensing

no code implementations28 May 2018 Wojciech Czaja, Neil Fendley, Michael Pekala, Christopher Ratto, I-Jeng Wang

This paper considers attacks against machine learning algorithms used in remote sensing applications, a domain that presents a suite of challenges that are not fully addressed by current research focused on natural image data such as ImageNet.

Satellite Image Classification

Superresolution of Noisy Remotely Sensed Images Through Directional Representations

no code implementations27 Feb 2016 Wojciech Czaja, James M. Murphy, Daniel Weinberg

We justify the use of shearlets mathematically, before presenting a denoising single-image superresolution algorithm that combines the shearlet transform with sparse mixing estimators (SME).

Denoising Edge Detection +1

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