Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

The overall architecture of the network.

More »

Fig 1 Expand

Fig 2.

Multi-scale pyramid convolution kernel.

More »

Fig 2 Expand

Fig 3.

Grouped convolution.

More »

Fig 3 Expand

Table 1.

PyconvResNet50 convolution kernel size information.

More »

Table 1 Expand

Fig 4.

Multi-attention module.

More »

Fig 4 Expand

Fig 5.

Channel attention module.

More »

Fig 5 Expand

Fig 6.

Spatial attention module.

More »

Fig 6 Expand

Table 2.

Details of the three datasets.

More »

Table 2 Expand

Table 3.

Top1 accuracy (%) of convolution combinations with different sizes on CUB-200-2011.

More »

Table 3 Expand

Table 4.

Experimental results of ablation.

Top1 accuracy (%) on CUB-200-2011.

More »

Table 4 Expand

Fig 7.

Back propagation saliency map.

More »

Fig 7 Expand

Fig 8.

Visualization of attention.

More »

Fig 8 Expand

Fig 9.

The test accuracy curve and train loss curve on CUB-200-2011, Stanford Cars and Stanford Dogs datasets.

More »

Fig 9 Expand

Table 5.

Comparison results on CUB-200-2011.

More »

Table 5 Expand

Table 6.

Comparison results on Stanford Dogs and Stanford Cars.

More »

Table 6 Expand