paper-with-me

Papers

GEOMETRIC AUGMENTATION FOR ROBUST NEURAL NETWORK CLASSIFIERS

2019-05-01 · ICLR 2019 5 · Robert M. Taylor, Yusong Tan

We introduce a novel geometric perspective and unsupervised model augmentation framework for transforming traditional deep (convolutional) neural networks into adversarially robust classifiers. Class-conditional probability densities based on Bayesian nonparametric mixtures of factor analyzers (BNP-MFA) over the input space are used to design soft decision labels for feature to label isometry. Classconditional distributions over features are also learned using BNP-MFA to develop plug-in maximum a posterior (MAP) classifiers to replace the traditional multinomial logistic softmax classification layers. This novel unsupervised augmented framework, which we call geometrically robust networks (GRN), is applied to CIFAR-10, CIFAR-100, and to Radio-ML (a time series dataset for radio modulation recognition). We demonstrate the robustness of GRN models to adversarial attacks from fast gradient sign method, Carlini-Wagner, and projected gradient descent.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationTime SeriesTime Series Analysis

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Manitest: Are classifiers really invariant?

2015-07-23 · Alhussein Fawzi, Pascal Frossard

Invariance to geometric transformations is a highly desirable property of automatic classifiers in many image recognition tasks. Nevertheless, it is unclear to which extent state-of-the-art classifiers are invariant to b…

Data Augmentation

Ensemble Augmentation for Deep Neural Networks Using 1-D Time Series Vibration Data

2021-08-06 · Atik Faysal, Ngui Wai Keng, M. H. Lim

Time-series data are one of the fundamental types of raw data representation used in data-driven techniques. In machine condition monitoring, time-series vibration data are overly used in data mining for deep neural netw…

Data AugmentationGenerative Adversarial NetworkTime SeriesTime Series Analysis+1

Geometric Filtering of LLM-Generated Samples for Few-Shot Text Classification

2026-08-14 · Benjamín Schindler, Gonzalo A. Ruz arxiv

Large language models (LLMs) can generate synthetic training data for text classification, but the quality of generated samples is heterogeneous: some fall in correct class regions of the embedding space while others lan…

Few-Shot Text Classification

Producing Plankton Classifiers that are Robust to Dataset Shift

2024-01-25 · Cheng Chen, Sreenath Kyathanahally, Marta Reyes, Stefanie Merkli 외

Modern plankton high-throughput monitoring relies on deep learning classifiers for species recognition in water ecosystems. Despite satisfactory nominal performances, a significant challenge arises from Dataset Shift, wh…

Diagnostic

Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now

2023-11-28 · CVPR 2024 1 · Ayush Sarkar, Hanlin Mai, Amitabh Mahapatra, Svetlana Lazebnik 외

Generative models can produce impressively realistic images. This paper demonstrates that generated images have geometric features different from those of real images. We build a set of collections of generated images, p…