内容相似度驱动的卷积神经网络
Convolutional Neural Networks Driven by Content Similarity
提出一种基于内容相似度的卷积聚合机制，通过排序操作将特征相似度转化为相对位置信息，使卷积能像自注意力一样聚合信息，为改进CNN的表征能力提供了可复用的技术思路。
原文依据 we introduce a mechanism for CNNs to aggregate information based on content similarity--an ability analogous to the self-attention mechanism.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论尽管卷积神经网络（CNN）近年来持续演进，Transformer在计算机视觉领域日益流行。本工作为CNN引入一种基于内容相似度聚合信息的机制——一种类似于自注意力机制的能力。我们通过提出一种排序操作来实现这一点，该操作将令牌间的特征相似度转化为相对位置信息：具体而言，重新排列令牌，使特征相似度更高的令牌彼此更靠近。该方法使卷积操作能够间接转化为由内容相似度驱动的聚合模式。实验表明，我们提出的名为Ego的模型在各种任务上取得了有前景的结果，凸显了CNN尚未挖掘的潜力。代码和模型已公开于 https://github.com/essenceoftheworld/ego。
英文原文摘要 931 字符
Although convolutional neural networks (CNNs) have continued to evolve in recent years, Transformers have become increasingly popular in the field of computer vision. In this work, we introduce a mechanism for CNNs to aggregate information based on content similarity--an ability analogous to the self-attention mechanism. We achieve this by proposing a sorting operation that transforms the feature similarity between tokens into relative positional information: specifically, rearranging tokens such that tokens with higher feature similarity are placed closer together. This approach allows convolution operations to be indirectly transformed into an aggregation mode driven by content similarity. Experiments show that our proposed model, named Ego, achieves promising results across various tasks, underscoring the untapped potential of CNNs. Code and models are publicly available at https://github.com/essenceoftheworld/ego.