Re:ImageNet contains naturally occurring Apple NeuralHash co...
by snet0 on Thursday August 19, 2021 @06:16PM
(#28240035)
Based on the pigeonhole principle alone, it will always be the case that collisions exist. The size of the digest is very likely smaller than the size of any given image.
[ Parent
| on HN ]
Re:ImageNet contains naturally occurring Apple NeuralHash co...
by SilasX on Thursday August 19, 2021 @09:09PM
(#28241279)
How is that relevant to whether “per image” or “Per image pair” is the right metric?
Heck, how is it relevant to anything given that hash functions avoid collisions in practice, even given the pigeonhole principle?