Re:Alice in Wonderland: Simple Tasks Showing Complete Reason...
by GaggiX on Wednesday June 05, 2024 @02:40PM
(#40588686)
If the model is first pre-trained on unlabeled images, then it takes about 10 labeled images of cats and 10 labeled images of dogs to train a (possibly strong) classifier (example: DINOv2), I doubt humans will do better.
[ Parent
| on HN ]
Re:Alice in Wonderland: Simple Tasks Showing Complete Reason...
by TeMPOraL on Wednesday June 05, 2024 @05:04PM
(#40590607)
That's a good point; when comparing performance with humans, one has to remember that a human spends years of training on unlabeled images in form of continuous video stream, on top of audio streams and other senses, before they're able to communicate with you so you could test them.