Convolutional Neural Networks
Inception-v3
Introduced by Szegedy et al. in Rethinking the Inception Architecture for Computer VisionInception-v3 is a convolutional neural network architecture from the Inception family that makes several improvements including using Label Smoothing, Factorized 7 x 7 convolutions, and the use of an auxiliary classifer to propagate label information lower down the network (along with the use of batch normalization for layers in the sidehead).
Source: Rethinking the Inception Architecture for Computer Vision
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 17 | 14.91% |
| General Classification | 15 | 13.16% |
| Classification | 13 | 11.40% |
| Adversarial Attack | 5 | 4.39% |
| Quantization | 4 | 3.51% |
| Image Captioning | 3 | 2.63% |
| Semantic Segmentation | 3 | 2.63% |
| Management | 3 | 2.63% |
| Object Recognition | 2 | 1.75% |
Auxiliary Classifier
Convolution
Dense Connections
Dropout
Inception-v3 Module
Label Smoothing
Max Pooling
Softmax
