Can I read CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective on EtoBox?

CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective by Yasuki, Shunsuke; Taki, Masato is a scholarly article available to read on EtoBox.

What is CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective about?

Recently, convolutional neural networks (CNNs) with large size kernels have attracted much attention in the computer vision field, following the success of the Vision Transformers. Large kernel CNNs have been reported to perform well in downstream vision tasks as well as in classification performance. The reason for the high-performance of large kernel CNNs in downstream tasks has been attributed to the large effective receptive field (ERF) produced by large size kernels, but this view has not been fully tested. We therefore revisit the performance of large kernel CNNs in downstream task, focusing on the weakly supervised object localization (WSOL) task. WSOL, a difficult downstream task that is not fully supervised, provides a new angle to explore the capabilities of the large kernel CNNs. Our study compares the modern large kernel CNNs ConvNeXt, RepLKNet, and SLaK to test the validity of the naive expectation that ERF size is important for improving downstream task performance. Our analysis of the factors contributing to high performance provides a different perspective, in which the main factor is feature map improvement. Furthermore, we find that modern CNNs are robust to the C

Author

Yasuki, Shunsuke; Taki, Masato

Published

2024

Language

EN