Skip to main content
. Author manuscript; available in PMC: 2024 Jul 12.
Published in final edited form as: IEEE Trans Pattern Anal Mach Intell. 2019 Jan 9;42(4):988–997. doi: 10.1109/TPAMI.2019.2891600

Fig. 3. Joint embeddings, using weighted MA of the three sets of images, where the noiseless dataset is used for the images of the duck, but the noisy data used for the cat and pig images.

Fig. 3

In all cases we show all three datasets’ embedding together. Left: Applying no weighting (standard MA). Centre left: Weighting the noisy cat images by a factor of 10. Centre right: Weighting the noisy pig images by a factor of 10. Right: Weighting the noiseless duck images by a factor of 10. It is clear that only in the final case, where the noiseless dataset is weighted, is the original manifold structure cleanly recovered. The idea behind our MA scheme is that it produces joint embeddings like that on the right of this figure rather than like those on the left.