paper-with-me

Papers

Generatively Augmented Neural Network Watchdog for Image Classification Networks

2021-09-07 · Justin M. Bui, Glauco A. Amigo, Robert J. Marks II

The identification of out-of-distribution data is vital to the deployment of classification networks. For example, a generic neural network that has been trained to differentiate between images of dogs and cats can only classify an input as either a dog or a cat. If a picture of a car or a kumquat were to be supplied to this classifier, the result would still be either a dog or a cat. In order to mitigate this, techniques such as the neural network watchdog have been developed. The compression of the image input into the latent layer of the autoencoder defines the region of in-distribution in the image space. This in-distribution set of input data has a corresponding boundary in the image space. The watchdog assesses whether inputs are in inside or outside this boundary. This paper demonstrates how to sharpen this boundary using generative network training data augmentation thereby bettering the discrimination and overall performance of the watchdog.

📄 PDF Abstract BibTeX arXiv:2109.06168

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationData Augmentationimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Symbiotic Hybrid Neural Network Watchdog For Outlier Detection

2021-02-28 · Justin Bui, Robert J. Marks II

Neural networks are largely black boxes. A neural network trained to classify fruit may classify a picture of a giraffe as a banana. A neural network watchdog's job is to identify such inputs, allowing a classifier to di…

Outlier Detection

Autoencoder Watchdog Outlier Detection for Classifiers

2020-10-24 · Justin Bui, Robert J Marks II

Neural networks have often been described as black boxes. A generic neural network trained to differentiate between kittens and puppies will classify a picture of a kumquat as a kitten or a puppy. An autoencoder watch do…

Outlier Detectionregression

Cascade Watchdog: A Multi-tiered Adversarial Guard for Outlier Detection

2021-08-20 · Glauco Amigo, Justin M. Bui, Charles Baylis, Robert J. Marks

The identification of out-of-distribution content is critical to the successful implementation of neural networks. Watchdog techniques have been developed to support the detection of these inputs, but the performance can…

Outlier DetectionOut-of-Distribution Detection

GASE: Generatively Augmented Sentence Encoding

2024-11-07 · Manuel Frank, Haithem Afli

We propose an approach to enhance sentence embeddings by applying generative text models for data augmentation at inference time. Unlike conventional data augmentation that utilises synthetic training data, our approach …

Data AugmentationSemantic Textual SimilaritySentenceSentence Embeddings+1

Pluto: A Deep Learning Based Watchdog for Anti Money Laundering

2019-08-01 · WS 2019 8 · Hao-Yuan Chen, Shang-Xuan Zou, Cheng-Lung Sung
Deep Learning