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

Pablo Rivas; Gisela Bichler; Tomas Cerny; Laurie Giddens; Stacie Petter

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

Computer Vision and Pattern Recognition 2024-09-11 v1 Machine Learning

Authors: Pablo Rivas , Gisela Bichler , Tomas Cerny , Laurie Giddens , Stacie Petter

Abstract

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.

Keywords

image representation learning encoder-decoder architecture representation learning

Cite

@article{arxiv.2409.06187,
  title  = {Bottleneck-based Encoder-decoder ARchitecture (BEAR) for Learning Unbiased Consumer-to-Consumer Image Representations},
  author = {Pablo Rivas and Gisela Bichler and Tomas Cerny and Laurie Giddens and Stacie Petter},
  journal= {arXiv preprint arXiv:2409.06187},
  year   = {2024}
}

Comments

2022 LXAI Workshop at the 39th International Conference on Machine Learning (ICML), Baltimore, Maryland

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

Abstract

Keywords

Cite

Comments

Related papers