video thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Constrained Semi-Supervised Learning using Attributes and Comparative Attributes

Published on Feb 4, 20256566 Views

We consider the problem of semi-supervised bootstrap learning for scene categorization. Existing semi-supervised approaches are typically unreliable and face semantic drift because the learning task

Related categories

Presentation

Constrained Semi-Supervised Learning Using Attributes and Comparative Attributes00:00
Big-data01:00:18
Unsupervised10:06:11
Semi-Supervised14:46:14
Semi-Supervised Bootstrapping (1)17:39:08
Semi-Supervised Bootstrapping (2)29:10:46
Semi-Supervised Bootstrapping (3)30:36:14
Semi-Supervised Bootstrapping (4)31:54:19
Semi-Supervised Graph-baesd Methods38:39:55
Binary Attributes (BA) (1)55:38:17
Binary Attributes (BA) (2)57:59:56
Binary Attributes (BA) (3)59:19:07
Auditorium (1)63:59:19
Auditorium (2)65:13:31
Auditorium (3)68:49:08
Sharing via Dissimilarity72:52:55
Amphitheatre, Auditorium (1)77:42:27
Amphitheatre, Auditorium (2)79:39:07
Amphitheatre, Auditorium (3)81:44:09
Dissimilarity Comparative Attributes (1)85:51:00
Dissimilarity Comparative Attributes (2)88:33:32
Dissimilarity Comparative Attributes (3)91:29:33
Comparative Attributes94:04:25
Selected Candidates (1)102:16:04
Selected Candidates (2)103:09:11
Promoted Instances104:25:11
Introspection119:49:14
Amphitheatre132:12:07
Control Experiments (1)141:35:07
Control Experiments (2)149:20:45
Control Experiments (3)151:00:07
Control Experiments (4)152:59:27
Control Experiments (5)153:58:48
Control Experiments (6)155:51:33
Control Experiments (7)158:57:16
Banquet Hall161:11:09
Control Experiments168:45:20
Co-training (Small Scale)170:35:42
Bedroom172:58:14
Scene Classification177:21:46
Co-Training (Large Scale)179:10:38