提出BEAR架构，用残差连接融合多特征提取机制，学习无偏图像表示。
Bottleneck-based Encoder-decoder ARchitecture (BEAR) for Learning Unbiased Consumer-to-Consumer Image Representations
- 基于残差连接的多特征提取融合，构建自编码器结构。
- 在多个数据集上验证了其学习丰富表征的能力。
- 适用于电商平台中犯罪活动图像分析，具实际应用价值。
无偏表示学习仍是特定应用场景下的研究课题。新架构通常通过组合基础组件解决具体问题。本文提出多种图像特征提取机制，结合残差连接，在自编码器框架下编码感知图像信息。所用图像数据旨在支持更广泛的研究，涉及消费者对消费者在线平台中的犯罪活动问题。初步结果表明，该架构能利用自身及其他图像数据集，学习到丰富的表征空间，有效应对识别出的关键挑战。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。