Very Deep Convolutional Networks for Large-Scale Image Recognition
Citations
1,269 citations
1,264 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...Pre-trained AlexNet, GoogLeNet, VGG-16 We used AlexNet (Krizhevsky et al., 2012), GoogLeNet (Szegedy et al., 2015) and VGG-16 (Simonyan & Zisserman, 2015) for the evaluation reported in Figure 4....
[...]
...Human observers show a striking bias towards responding with the shape category (95.9% of correct decisions).3 This pattern is reversed for CNNs, which show a clear bias towards responding with the texture category (VGG-16: 17.2% shape vs. 82.8% texture; GoogLeNet: 31.2% vs. 68.8%; AlexNet: 42.9% vs. 57.1%; ResNet-50: 22.1% vs. 77.9%)....
[...]
...The same images were fed to four CNNs pre-trained on standard ImageNet, namely AlexNet (Krizhevsky et al., 2012), GoogLeNet (Szegedy et al., 2015), VGG-16 (Simonyan & Zisserman, 2015) and ResNet-50 (He et al., 2015)....
[...]
...The learning rate for AlexNet was set to 0.001 and for VGG-16 to 0.01 initially; both learning rates were multiplied by 0.1 after 20 and 40 epochs of training (60 epochs in total)....
[...]
...Training AlexNet, VGG-16 on SIN For the evaluation of model biases after training on SIN (Figure 11), we obtained the model architectures from torchvision.models and trained the networks under identical circumstances as ResNet-50....
[...]
1,263 citations
1,261 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...SMem [22] uses GoogLeNet [20] and the rest all use VGGNet [19], and Ours+VGG outperforms them by 0....
[...]
...SMem [22] uses GoogLeNet [18] and the rest all use VGGNet [17], and Ours+VGG outperforms them by 0.2% on test-dev (DMN+ [21])....
[...]
...Following [23], we rescale the image to 448× 448, and then take the activation from the last pooling layer of VGGNet [19] or ResNet [7] as its feature....
[...]
...Following [23], we rescale the image to 448× 448, and then take the activation from the last pooling layer of VGGNet [17] or Deep Residual network [6] as its feature....
[...]
1,240 citations
References
49,639 citations
21,729 citations
9,803 citations
9,775 citations
6,061 citations