Sign inSign up
CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples

Published on Oct 24, 20164459 Views

Filip Radenović

Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks. However, this achievement is preceded by extreme manual annotation in order to perform either t

ECCV 2016 - Amsterdam

Related categories

Computer Vision

Chapter list

CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples/100:00
CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples/200:08
CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples/300:12
CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples/400:32
CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples/500:42
CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples/600:59
CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples/701:09
Instance Retrieval Challenges/101:18
Instance Retrieval Challenges/201:36
Instance Retrieval Challenges/301:46
Instance Retrieval Challenges/401:57
Instance Retrieval Challenges/502:10
“Lots of Training Examples”/102:13
“Lots of Training Examples”/202:17
“Lots of Training Examples”/302:29
“Lots of Training Examples”/402:33
“Lots of Training Examples”/502:45
Off-the-shelf CNN02:50
Annotations for CNN Image Retrieval03:12
CNN learns from BoW – Training Data/104:31
CNN learns from BoW – Training Data/205:01
Hard Negative Examples/105:17
Hard Negative Examples/205:32
Hard Negative Examples/305:44
Hard Negative Examples/405:57
Hard Positive Examples06:12
CNN Siamese Learning/107:14
CNN Siamese Learning/207:16
CNN Siamese Learning/307:27
CNN Siamese Learning/407:32
CNN Siamese Learning/507:36
CNN Siamese Learning/607:40
Whitening and dimensionality reduction/107:55
Whitening and dimensionality reduction/208:13
Whitening and dimensionality reduction/308:22
Whitening and dimensionality reduction/408:38
Experiments – datasets/108:46
Experiments – datasets/209:00
Experiments – Learning (AlexNet)/109:06
Experiments – Learning (AlexNet)/209:12
Experiments – Learning (AlexNet)/309:14
Experiments – Learning (AlexNet)/409:15
Experiments – Learning (AlexNet)/509:17
Experiments – Learning (AlexNet)/609:19
Experiments – Learning (AlexNet)/709:22
Experiments – Over-fitting and Generalization/109:27
Experiments – Over-fitting and Generalization/209:41
State-of-the-art/109:49
State-of-the-art/210:10
State-of-the-art/310:23
Teacher vs. Student/110:33
Teacher vs. Student/211:04
Teacher vs. Student/311:14
Teacher vs. Student/411:25
Teacher vs. Student/511:32
Teacher vs. Student/611:40
Teacher vs. Student/711:45
Teacher vs. Student/811:50
Teacher vs. Student/911:59
Conclusion12:02