no code implementations • ICLR 2020 • Miao Yang and Ke Hu, Chongyi Li, Zhiqiang Wei
By substituting the inception module with the I-A module, the Inception-ResnetV2 network achieves a 10. 7% top1 error rate and a 0% top5 error rate on the subset of ILSVRC-2012, which further illustrates the function of the background attention in the image classifications.