Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/kieranlitschel/contextualised-image-classifiers
Mahajan et al. and Yalniz et al. demonstrate the benefit of pre-training on large unlabeled image datasets using user tags as labels for weak-supervision. We take this approach further, considering whether the use of user tags in large labeled image datasets is beneficial.
https://github.com/kieranlitschel/contextualised-image-classifiers
computer-vision flickr hashtags image-classification object-detection openimages social-media tensorflow usertags yfcc100m
Last synced: 25 days ago
JSON representation
Mahajan et al. and Yalniz et al. demonstrate the benefit of pre-training on large unlabeled image datasets using user tags as labels for weak-supervision. We take this approach further, considering whether the use of user tags in large labeled image datasets is beneficial.
- Host: GitHub
- URL: https://github.com/kieranlitschel/contextualised-image-classifiers
- Owner: KieranLitschel
- Created: 2020-01-16T13:04:12.000Z (almost 5 years ago)
- Default Branch: master
- Last Pushed: 2022-12-08T07:29:21.000Z (about 2 years ago)
- Last Synced: 2024-10-28T16:59:30.227Z (2 months ago)
- Topics: computer-vision, flickr, hashtags, image-classification, object-detection, openimages, social-media, tensorflow, usertags, yfcc100m
- Language: Python
- Homepage:
- Size: 317 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 17
-
Metadata Files:
- Readme: README.md