测试时找回被下采样丢弃的激活值，提升模型性能
Deep Nets with Subsampling Layers Unwittingly Discard Useful Activations at Test-Time
- 提出搜索并聚合被下采样丢弃的激活图
- 在九种架构上均提升图像分类与分割准确率
- 无需修改模型，可与现有测试增强技术配合
下采样层通过丢弃部分特征图来降低空间维度，有助于网络学习高层语义。然而，我们发现这些被丢弃的激活值实际上对预测有帮助。为此，我们提出一种搜索与聚合方法，在测试时动态利用这些被丢弃的激活图。该方法应用于图像分类和语义分割任务，在多个数据集上的九种不同架构上均取得一致性能提升，且可与现有测试时增强技术互补。代码已开源：https://github.com/ca-joe-yang/discard-in-subsampling。
原文摘要 · Abstract (English)
Subsampling layers play a crucial role in deep nets by discarding a portion of an activation map to reduce its spatial dimensions. This encourages the deep net to learn higher-level representations. Contrary to this motivation, we hypothesize that the discarded activations are useful and can be incorporated on the fly to improve models' prediction. To validate our hypothesis, we propose a search and aggregate method to find useful activation maps to be used at test time. We applied our approach to the task of image classification and semantic segmentation. Extensive experiments over nine different architectures on multiple datasets show that our method consistently improves model test-time performance, complementing existing test-time augmentation techniques. Our code is available at https://github.com/ca-joe-yang/discard-in-subsampling.
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。