Bottleneck-based Encoder-decoder ARchitecture (BEAR) for Learning Unbiased Consumer-to-Consumer Image Representations

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Rivas, Pablo, Bichler, Gisela, Cerny, Tomas, Giddens, Laurie, Petter, Stacie
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913495479484416
author Rivas, Pablo
Bichler, Gisela
Cerny, Tomas
Giddens, Laurie
Petter, Stacie
author_facet Rivas, Pablo
Bichler, Gisela
Cerny, Tomas
Giddens, Laurie
Petter, Stacie
contents Unbiased representation learning is still an object of study under specific applications and contexts. Novel architectures are usually crafted to resolve particular problems using mixtures of fundamental pieces. This paper presents different image feature extraction mechanisms that work together with residual connections to encode perceptual image information in an autoencoder configuration. We use image data that aims to support a larger research agenda dealing with issues regarding criminal activity in consumer-to-consumer online platforms. Preliminary results suggest that the proposed architecture can learn rich spaces using ours and other image datasets resolving important challenges that are identified.
format Preprint
id arxiv_https___arxiv_org_abs_2409_06187
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bottleneck-based Encoder-decoder ARchitecture (BEAR) for Learning Unbiased Consumer-to-Consumer Image Representations
Rivas, Pablo
Bichler, Gisela
Cerny, Tomas
Giddens, Laurie
Petter, Stacie
Computer Vision and Pattern Recognition
Machine Learning
I.2.10; I.5.1; K.4.1; H.3.3; I.2.6
Unbiased representation learning is still an object of study under specific applications and contexts. Novel architectures are usually crafted to resolve particular problems using mixtures of fundamental pieces. This paper presents different image feature extraction mechanisms that work together with residual connections to encode perceptual image information in an autoencoder configuration. We use image data that aims to support a larger research agenda dealing with issues regarding criminal activity in consumer-to-consumer online platforms. Preliminary results suggest that the proposed architecture can learn rich spaces using ours and other image datasets resolving important challenges that are identified.
title Bottleneck-based Encoder-decoder ARchitecture (BEAR) for Learning Unbiased Consumer-to-Consumer Image Representations
topic Computer Vision and Pattern Recognition
Machine Learning
I.2.10; I.5.1; K.4.1; H.3.3; I.2.6
url https://arxiv.org/abs/2409.06187