Improving the Resolution of CNN Feature Maps Efficiently with Multisampling
We describe a new class of subsampling techniques for CNNs, termed multisampling, that significantly increases the amount of information kept by feature maps through subsampling layers. One version of our method, which we call checkered subsampling, significantly improves the accuracy of state-of-the-art architectures such as DenseNet and ResNet without any additional parameters and, remarkably, improves the accuracy of certain pretrained ImageNet models without any training or fine-tuning. We glean possible insight into the nature of data augmentations and demonstrate experimentally that coarse feature maps are bottlenecking the performance of neural networks in image classification.
PDF Abstract
Datasets
Add Datasets
introduced or used in this paper
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Methods
1x1 Convolution •
Average Pooling •
Batch Normalization •
Bottleneck Residual Block •
Concatenated Skip Connection •
Convolution •
Dense Block •
Dense Connections •
DenseNet •
Dropout •
Global Average Pooling •
Kaiming Initialization •
Max Pooling •
ReLU •
Residual Block •
Residual Connection •
ResNet •
Softmax
