Inception networks (Going Deeper with Convolutions, https://arxiv.org/abs/1409.4842) were introduced in 2014, when they won the ImageNet challenge of that year (there seems to be a pattern here). Since then, the authors have released multiple improvements (versions) of the architecture.
Fun fact: the name Inception comes in part from the We need to go deeper internet meme, related to the movie Inception.
The idea behind Inception networks started from the basic premise that the objects in an image have different scales. A distant object might take up a small region of the image, but the same object, once nearer, might take up the majority of the image. This presents a difficulty for standard CNNs, where the neurons in the different layers have a fixed receptive field size as imposed on the input image. A regular network might be a good detector...
