Analysis of Large-Scale Visual Recognition - Bay Area Vision Meeting

Analysis of Large-Scale Visual Recognition - Bay Area Vision Meeting

Meta Developers via YouTube Direct link

Intro

1 of 16

1 of 16

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Analysis of Large-Scale Visual Recognition - Bay Area Vision Meeting

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Large-scale recognition
  3. 3 IMAGENET Large Scale Visual Recognition Challenge (ILSVRC) 2010-2012
  4. 4 Variety of object classes in ILSVRC
  5. 5 ILSVRC Task 1: Classification
  6. 6 ILSVRC Task 2: Classification + Localization
  7. 7 ILSVRC (2012)
  8. 8 Chance Performance of Localization
  9. 9 Level of clutter
  10. 10 SuperVision (SV)
  11. 11 Difference in accuracy: SV versus VGG
  12. 12 Cumulative accuracy across scales Classification only
  13. 13 Textured objects (ILSVRC-500)
  14. 14 Textured objects (416 classes)
  15. 15 Localizing textured objects (416 classes, same average object scale at each level of texture)
  16. 16 ILSVRC 2013 with large-scale object detection

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.