Perceptual Hashing

%3 cluster_8d831c01_2a4d_4ca1_a1f1_11b7826f7914 Perceptual Hashing _d49e8000_18cf_458d_b4c8_0a5cda20cad0 pHash _d49e8000_18cf_458d_b4c8_0a5cda20cad0->__0:cluster_8d831c01_2a4d_4ca1_a1f1_11b7826f7914 _20f73b78_fd65_404b_8b54_5ff3da65d442 Word embedding __1:cluster_8d831c01_2a4d_4ca1_a1f1_11b7826f7914->_20f73b78_fd65_404b_8b54_5ff3da65d442

Semantics aware hashing techniques where hashes can be compared and similar files should yield similar hashes.

Kind of a non ML-based Word embedding but for other content types, like images.