ImageNet is assembled and released

Assembled from 19 blocks · 1 evidence · 15 related

1. Story
2. Fei-Fei Li's group began building a labelled image collection at a scale nobody had attempted, organised on the WordNet noun hierarchy and annotated largely through crowdsourced work, and released it from 2009. The bet was explicit and contrarian: that recognition was limited by the absence of data rather than by algorithm design. The annual challenge run on a subset of it from 2010 turned that bet into a public scoreboard, which is what allowed the 2012 result to be recognised immediately as a result.
3. Knowledge
4. ImageNet
5. Fei-Fei Li
6. ImageNet is assembled and released
7. Connections
8. ImageNet
9. Fei-Fei Li
10. Deep learning
11. Fei-Fei Li
12. ImageNet is assembled and released
13. A deep convolutional network wins the ImageNet challenge
14. ImageNet
15. Benchmark saturation
16. ImageNet is assembled and released
17. The AI Index records both fast benchmark movement and doubts about benchmarks
18. Evidence
19. An eight-layer convolutional network — five convolutional and three fully connected layers — trained on graphics processors with dropout regularisation achieved a top-5 error rate of 15.3% at ILSVRC 2012 against 26.2% for the second-placed entry, learning hierarchical features rather than using hand-designed ones. V55 verification basis: the paper was not fetched. The 15.3% and 26.2% figures and the architecture description were carried in multiple retrieved summaries and in a hosted copy of the paper itself, but the attribution in those summaries is to secondary explainers as often as to the paper, and a curator should confirm both error rates against the ILSVRC 2012 results table before publication.