Bottleneck-based Encoder-decoder ARchitecture (BEAR) for Learning Unbiased Consumer-to-Consumer Image Representations
This work addresses criminal activity detection in online platforms, but it appears incremental as it combines existing techniques like autoencoders and residual connections without a clear breakthrough.
The paper tackles the problem of learning unbiased image representations for consumer-to-consumer platforms by proposing a bottleneck-based encoder-decoder architecture with residual connections, and preliminary results indicate it can learn rich feature spaces on various datasets.
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.