To provide a compact and efficient input to the brain, sensory systems separate the incoming information into parallel feature channels. In the visual system, parallel processing starts in the retina. Here, the image is decomposed into multiple retinal ganglion cell (RGC) types, each selective for a specific set of visual features like motion, contrast or edges. Recent work in mice provides a thorough classification of RGCs, revealing that the retina sends approx. 40 distinct information channels to the brain. In my talk, I will summarize our recent work on the neural mechanisms underlying this great diversity and on how the neural selectivity for distinct visual features arises across the retinal network. With this, we hope to increase our understanding of how the mammalian retina processes the stream of incoming visual information to extract relevant features from the environment.