Michael Gormish, Research Manager at Clarifai, presents the “Machine Learning- based Image Compression: Ready for Prime Time?” tutorial at the May 2019 Embedded Vision Summit.
Computer vision is undergoing dramatic changes because deep learning techniques are now able to solve complex non-linear problems. Computer vision pipelines used to consist of hand engineered stages mathematically optimized for some carefully chosen objective function. These pipelines are being replaced with machine- learned stages or end-to-end learning techniques where enough ground truth data is available.
Similarly, for decades image compression has relied on hand crafted algorithm pipelines, but recent efforts using deep learning are reporting higher image quality than that provided by conventional techniques. Is it time to replaced discrete cosine transforms with machine-learned compression techniques?
This talk examines practical aspects of deep learned image compression systems as compared with traditional approaches. Gormish considers memory, computation and other aspects, in addition to rate-distortion, to see when ML-based compression should be considered or avoided. He also discusses approaches using a combination of machine learned and traditional techniques.
