Deep Pyramidal Residual Networks with Separated Stochastic Depth
Yoshihiro Yamada, Masakazu Iwamura, Koichi Kise
TL;DR
This paper introduces a novel deep pyramidal residual network that combines ResDrop and PyramidNet techniques, achieving superior accuracy on CIFAR-100 by outperforming existing ResNet-based models.
Contribution
The paper presents a new deep pyramidal residual network that effectively integrates ResDrop and PyramidNet, leading to improved object recognition performance.
Findings
Achieved 16.18% error rate on CIFAR-100
Outperformed PyramidNet and ResNeXt models
Demonstrated the effectiveness of combined ResNet improvements
Abstract
On general object recognition, Deep Convolutional Neural Networks (DCNNs) achieve high accuracy. In particular, ResNet and its improvements have broken the lowest error rate records. In this paper, we propose a method to successfully combine two ResNet improvements, ResDrop and PyramidNet. We confirmed that the proposed network outperformed the conventional methods; on CIFAR-100, the proposed network achieved an error rate of 16.18% in contrast to PiramidNet achieving that of 18.29% and ResNeXt 17.31%.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · Domain Adaptation and Few-Shot Learning · Advanced Image and Video Retrieval Techniques
MethodsPyramidal Bottleneck Residual Unit · Average Pooling · ResNeXt Block · Zero-padded Shortcut Connection · Pyramidal Residual Unit · PyramidNet · Grouped Convolution · Bottleneck Residual Block · Global Average Pooling · Residual Block