PlaNet - Photo Geolocation with Convolutional Neural Networks · HackerPapers discussions

PlaNet - Photo Geolocation with Convolutional Neural Networks — mentioned by jefftk

Thu, 21 Nov 2019 14:14:33 GMT

Those pictures are not sufficiently anonymous; https://arxiv.org/abs/1602.05314 or just neighbors could easily see where she is. And the barcodes are easily visible on some of the boxes.

Paper and discussion history. A mention is not an endorsement.

PlaNet - Photo Geolocation with Convolutional Neural Networks — mentioned by aub3bhat

Wed, 31 May 2017 18:08:41 GMT

There are so many issues with this post, let me enumerate: 1. Straw man tweet by some non-practitioner which is used to set up the straw-man argument. 2. The whole Digits example is ridiculous, statisticians "love" toy problems to prove theorems & make "arguments" etc. ML is empirical and not just the performance but the entire pipeline from data to application matters. Let me illustrate: If your aim is to predict 1 vs 0 from images of digits. As an ML researcher I would write a program to synthesize images in all different combinations of fonts/font-color/background color/ location…

Paper and discussion history. A mention is not an endorsement.

PlaNet - Photo Geolocation with Convolutional Neural Networks — HN submission

Fri, 03 Mar 2017 23:43:10 GMT

PlaNet – Photo Geolocation with Convolutional Neural Networks

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

PlaNet - Photo Geolocation with Convolutional Neural Networks — mentioned by epistasis

Fri, 25 Nov 2016 21:20:08 GMT

Presumably more accurate than a single human, and you can do it with multiple humans and reaching a consensus. I remember an anecdote in physics class where an experiment required counting a certain number of events in time. A single person would occasionally blink and miss an event. But if you had two people, and you count how many people observed each event, you can solve for super-human accuracy using the estimated error rates of each person. See also this usage in the context of ML: https://arxiv.org/pdf/1602.05314v1.pdf

Paper and discussion history. A mention is not an endorsement.

PlaNet - Photo Geolocation with Convolutional Neural Networks — mentioned by daveloyall

Thu, 14 Apr 2016 17:50:19 GMT

Google did this already. http://arxiv.org/pdf/1602.05314.pdf

Paper and discussion history. A mention is not an endorsement.

PlaNet - Photo Geolocation with Convolutional Neural Networks — HN submission

Wed, 16 Mar 2016 03:47:48 GMT

PlaNet – Photo Geolocation with Convolutional Neural Networks

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

PlaNet - Photo Geolocation with Convolutional Neural Networks — mentioned by brudgers

Wed, 02 Mar 2016 14:00:14 GMT

Relevant paper: http://arxiv.org/pdf/1602.05314v1.pdf

Paper and discussion history. A mention is not an endorsement.