按年被提到
20192020 · 2 次2026
视觉、语音与图像生成›卷积网络与图像识别·arXiv:1904.00760 · cs.CV

Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet

Wieland Brendel, Matthias Bethge · 2019
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2020-02-05 · 最近 2020-12-06
2不同的人
2活跃月份
2讨论串
396被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Deep Neural Networks (DNNs) excel on many complex perceptual tasks but it has proven notoriously difficult to understand how they reach their decisions. We here introduce a high-performance DNN architecture on ImageNet whose decisions are considerably easier to explain. Our model, a simple variant of the ResNet-50 architecture called BagNet, classifies an image based on the occurrences of small local image features without taking into account their spatial ordering. This strategy is closely related to the bag-of-feature (BoF) models popular before the onset of deep learning and reaches a surprisingly high accuracy on ImageNet (87.6% top-5 for 33 x 33 px features and Alexnet performance for 17 x 17 px features). The constraint on local features makes it straight-forward to analyse how exactly each part of the image influences the classification. Furthermore, the BagNets behave similar to state-of-the art deep neural networks such as VGG-16, ResNet-152 or DenseNet-169 in terms of feature sensitivity, error distribution and interactions between image parts. This suggests that the improvements of DNNs over previous bag-of-feature classifiers in the last few years is mostly achieved by better fine-tuning rather than by qualitatively different decision strategies.

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b3kart · 2020-02

“I am not convinced the explanations we’d get from these models would be interpretable enough to drive their conceptual improvement. Deep nets just don’t learn nice interpretable features, nothing in the training objective makes them do so. E.g. they make use of really dubious features [1], and might not actually learn “hierarchies” of features as we thoug…”

Sometimes, requiring explanability is counterproductive原评论 ↗
评论sarosh · 2020-12

“See also W. Brendel and M. Bethge. "Approximating CNNs with bag-of-local-features models works surprisingly well on ImageNet." https://arxiv.org/abs/1904.00760 (which is referenced in this paper) and explains "[t]his suggests that the improvements of DNNs over previous bag-of-feature classifiers in the last few years is mostly achieved by better fine-tuni…”

Every Model Learned by Gradient Descent Is Approximately a Kernel Machine原评论 ↗