And the 'What the Internet could look like...' scroll down is simple yet truly elegant. Bravo.
1 karma · joined August 17, 2024
And the 'What the Internet could look like...' scroll down is simple yet truly elegant. Bravo.
I'm all for prizes and contests as a means of incentivizing creativity and innovation, but the lack of clarity on the above point (and thus what you both "get" and "give up" for winning) is disappointing.
"To learn the feature weight vector which best discriminates an im- age from a large “background” dataset, we employ the linear Sup- port Vector Machine (SVM) framework. We set up the learning problem following [Malisiewicz et al. 2011] which has demon- strated that a linear SVM can generalize even with a single positive example, provided that a very large amount of negative data is avail- able to “constrain the solution”. However, whereas in [Malisiewicz et al. 2011] the negatives are guaranteed not to be members of the positive class (that is why they are called negatives), here this is not the case. The “negatives” are just a dataset of images randomly sampled from a large Flickr collection, and there is no guarantee that some of them might not be very similar to the “positive” query image. Interestingly, in practice, this does not seem to hurt the SVM, suggesting that this is yet another new application where the SVM formalism can be successfully applied."
It would also be interesting to see a comparison of images where the features are less pronounced, e.g., matching landscape images. One can imagine uniform weighting approaches performing better where, for example, color is a more important matching criteria than form/features.