We propose a deep convolutional neural network architecture codenamed "Inception", which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC 2014). The main hallmark of this architecture is the improved utilization of the computing resources inside the network... (read more)
PDFTASK | DATASET | MODEL | METRIC NAME | METRIC VALUE | GLOBAL RANK | COMPARE |
---|---|---|---|---|---|---|
Image Classification | ImageNet | Inception V1 | Top 1 Accuracy | 69.8% | # 103 | |
Image Classification | ImageNet | Inception V1 | Top 5 Accuracy | 89.9% | # 80 | |
Image Classification | ImageNet | Inception V1 | Number of params | 5M | # 1 | |
Object Detection | ImageNet Detection | Inception V1 | MAP | 43.9% | # 1 |