按年被提到
20212021 · 4 次2026
视觉、语音与图像生成›ViT 与视觉新架构·arXiv:2105.07197 · cs.CV

Are Convolutional Neural Networks or Transformers more like human vision?

Shikhar Tuli, Ishita Dasgupta, Erin Grant, Thomas L. Griffiths · 2021
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2021-05-18 · 最近 2021-07-03
3不同的人
2活跃月份
3讨论串
168被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Modern machine learning models for computer vision exceed humans in accuracy on specific visual recognition tasks, notably on datasets like ImageNet. However, high accuracy can be achieved in many ways. The particular decision function found by a machine learning system is determined not only by the data to which the system is exposed, but also the inductive biases of the model, which are typically harder to characterize. In this work, we follow a recent trend of in-depth behavioral analyses of neural network models that go beyond accuracy as an evaluation metric by looking at patterns of errors. Our focus is on comparing a suite of standard Convolutional Neural Networks (CNNs) and a recently-proposed attention-based network, the Vision Transformer (ViT), which relaxes the translation-invariance constraint of CNNs and therefore represents a model with a weaker set of inductive biases. Attention-based networks have previously been shown to achieve higher accuracy than CNNs on vision tasks, and we demonstrate, using new metrics for examining error consistency with more granularity, that their errors are also more consistent with those of humans. These results have implications both for building more human-like vision models, as well as for understanding visual object recognition in humans.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论belter · 2021-07

“"... In this work, we follow a recent trend of in-depth behavioral analyses of neural network models that go beyond accuracy as an evaluation metric by looking at patterns of errors. Our focus is on comparing a suite of standard Convolutional Neural Networks (CNNs) and a recently-proposed attention-based network, the Vision Transformer (ViT), which relaxe…”

Are Convolutional Neural Networks or Transformers more like human vision?原评论 ↗
被提交为 story · 3 次