Inception-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 VisionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Classification | 16 | 12.80% |
General Classification | 15 | 12.00% |
Classification | 13 | 10.40% |
Adversarial Attack | 5 | 4.00% |
Quantization | 4 | 3.20% |
Object Detection | 3 | 2.40% |
Image Captioning | 3 | 2.40% |
Semantic Segmentation | 3 | 2.40% |
Management | 3 | 2.40% |