Skip to main content

2018 | OriginalPaper | Buchkapitel

Comparator Networks

verfasst von : Weidi Xie, Li Shen, Andrew Zisserman

Erschienen in: Computer Vision – ECCV 2018

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

The objective of this work is set-based verification, e.g. to decide if two sets of images of a face are of the same person or not. The traditional approach to this problem is to learn to generate a feature vector per image, aggregate them into one vector to represent the set, and then compute the cosine similarity between sets. Instead, we design a neural network architecture that can directly learn set-wise verification.
Our contributions are: (i) We propose a Deep Comparator Network (DCN) that can ingest a pair of sets (each may contain a variable number of images) as inputs, and compute a similarity between the pair – this involves attending to multiple discriminative local regions (landmarks), and comparing local descriptors between pairs of faces; (ii) To encourage high-quality representations for each set, internal competition is introduced for recalibration based on the landmark score; (iii) Inspired by image retrieval, a novel hard sample mining regime is proposed to control the sampling process, such that the DCN is complementary to the standard image classification models. Evaluations on the IARPA Janus face recognition benchmarks show that the comparator networks outperform the previous state-of-the-art results by a large margin.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Anhänge
Nur mit Berechtigung zugänglich
Fußnoten
1
In our training, we only use 4 facial landmarks, left-eye, right-eye, nose, mouth. The mouth landmarks are obtained by averaging the two landmarks at mouth corners.
 
2
This guarantees a probability of \(64\%\) that both templates contain 3 different images, and a probability of \(36\%\) that at least one template contains 3 identical image.
 
Literatur
1.
Zurück zum Zitat Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1106–1114 (2012) Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1106–1114 (2012)
2.
Zurück zum Zitat Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015) Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)
3.
Zurück zum Zitat He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR (2016) He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR (2016)
6.
Zurück zum Zitat Parkhi, O.M., Vedaldi, A., Zisserman, A.: Deep face recognition. In: Proceedings of BMVC (2015) Parkhi, O.M., Vedaldi, A., Zisserman, A.: Deep face recognition. In: Proceedings of BMVC (2015)
7.
Zurück zum Zitat Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: Proceedings of CVPR (2015) Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: Proceedings of CVPR (2015)
8.
Zurück zum Zitat Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Deepface: closing the gap to human-level performance in face verification. In: Proceedings of CVPR (2014) Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Deepface: closing the gap to human-level performance in face verification. In: Proceedings of CVPR (2014)
10.
Zurück zum Zitat Weinberger, K.Q., Blitzer, J., Saul, L.: Distance metric learning for large margin nearest neighbor classification. In: NIPS (2006) Weinberger, K.Q., Blitzer, J., Saul, L.: Distance metric learning for large margin nearest neighbor classification. In: NIPS (2006)
11.
Zurück zum Zitat Ustinova, E., Lempitsky, V.: Learning deep embeddings with histogram loss. In: NIPS (2016) Ustinova, E., Lempitsky, V.: Learning deep embeddings with histogram loss. In: NIPS (2016)
12.
Zurück zum Zitat Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017) Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:​1703.​07737 (2017)
13.
Zurück zum Zitat Whitelam, C., et al.: IARPA Janus Benchmark-B face dataset. In: CVPR Workshop on Biometrics (2017) Whitelam, C., et al.: IARPA Janus Benchmark-B face dataset. In: CVPR Workshop on Biometrics (2017)
14.
Zurück zum Zitat Maze, B., Adams, J., Duncan, J.A., Kalka, N., Miller, T., Otto, C., Jain, A.K., Niggel, W.T., Anderson, J., Cheney, J., Grother, P.: IARPA Janus Benchmark-C: face dataset and protocol. In: 11th IAPR International Conference on Biometrics (2018) Maze, B., Adams, J., Duncan, J.A., Kalka, N., Miller, T., Otto, C., Jain, A.K., Niggel, W.T., Anderson, J., Cheney, J., Grother, P.: IARPA Janus Benchmark-C: face dataset and protocol. In: 11th IAPR International Conference on Biometrics (2018)
15.
Zurück zum Zitat Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: Proceedings of CVPR (2007) Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: Proceedings of CVPR (2007)
17.
Zurück zum Zitat Luan, T., Xi, Y., Xiaoming, L.: Disentangled representation learning GAN for pose-invariant face recognition. In: Proceedings of CVPR (2017) Luan, T., Xi, Y., Xiaoming, L.: Disentangled representation learning GAN for pose-invariant face recognition. In: Proceedings of CVPR (2017)
18.
Zurück zum Zitat Yang, J., et al.: Neural aggregation network for video face recognition. In: Proceedings of CVPR (2017) Yang, J., et al.: Neural aggregation network for video face recognition. In: Proceedings of CVPR (2017)
19.
Zurück zum Zitat Xie, W., Zisserman, A.: Multicolumn networks for face recognition. In: Proceedings of BMVC (2018) Xie, W., Zisserman, A.: Multicolumn networks for face recognition. In: Proceedings of BMVC (2018)
20.
Zurück zum Zitat Li, H., Hua, G., Brandt, J., Yang, J.: Probabilistic elastic matching for pose variant face verification. In: Proceedings of CVPR (2013) Li, H., Hua, G., Brandt, J., Yang, J.: Probabilistic elastic matching for pose variant face verification. In: Proceedings of CVPR (2013)
21.
Zurück zum Zitat Parkhi, O.M., Simonyan, K., Vedaldi, A., Zisserman, A.: A compact and discriminative face track descriptor. In: Proceedings of CVPR (2014) Parkhi, O.M., Simonyan, K., Vedaldi, A., Zisserman, A.: A compact and discriminative face track descriptor. In: Proceedings of CVPR (2014)
22.
Zurück zum Zitat Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of ICLR (2015) Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of ICLR (2015)
23.
Zurück zum Zitat Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. In: Proceedings of ICLR (2015) Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. In: Proceedings of ICLR (2015)
24.
Zurück zum Zitat Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: Neural image caption generation with visual attention. In: Proceedings of ICML (2015) Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: Neural image caption generation with visual attention. In: Proceedings of ICML (2015)
25.
Zurück zum Zitat Zheng, H., Fu, J., Mei, T., Luo, J.: Learning multi-attention convolutional neural network for fine-grained image recognition. In: Proceedings of ICCV (2017) Zheng, H., Fu, J., Mei, T., Luo, J.: Learning multi-attention convolutional neural network for fine-grained image recognition. In: Proceedings of ICCV (2017)
26.
Zurück zum Zitat Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: NIPS (2015) Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: NIPS (2015)
27.
Zurück zum Zitat Santoro, A., Raposo, D., Barrett, D.G.T., Malinowski, M., Pascanu, R., Battaglia, P., Lillicrap, T.P.: A simple neural network module for relational reasoning. CoRR abs/1706.01427 (2017) Santoro, A., Raposo, D., Barrett, D.G.T., Malinowski, M., Pascanu, R., Battaglia, P., Lillicrap, T.P.: A simple neural network module for relational reasoning. CoRR abs/1706.01427 (2017)
28.
Zurück zum Zitat Lin, T.J., RoyChowdhury, A., Maji, S.: Bilinear CNN models for fine-grained visual recognition. In: Proceedings of ICCV (2015) Lin, T.J., RoyChowdhury, A., Maji, S.: Bilinear CNN models for fine-grained visual recognition. In: Proceedings of ICCV (2015)
29.
Zurück zum Zitat Vinyals, O., Blundell, C., Lillicrap, T., kavukcuoglu, k., Wierstra, D.: Matching networks for one shot learning. In: NIPS (2016) Vinyals, O., Blundell, C., Lillicrap, T., kavukcuoglu, k., Wierstra, D.: Matching networks for one shot learning. In: NIPS (2016)
30.
Zurück zum Zitat Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H.S., Hospedales, T.M.: Learning to compare: relation network for few-shot learning. In: Proceedings of CVPR (2018) Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H.S., Hospedales, T.M.: Learning to compare: relation network for few-shot learning. In: Proceedings of CVPR (2018)
31.
Zurück zum Zitat Felzenszwalb, P., Mcallester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: Proceedings of CVPR (2008) Felzenszwalb, P., Mcallester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: Proceedings of CVPR (2008)
32.
Zurück zum Zitat Thewlis, J., Bilen, H., Vedaldi, A.: Unsupervised learning of object landmarks by factorized spatial embeddings. In: Proceedings of ICCV (2017) Thewlis, J., Bilen, H., Vedaldi, A.: Unsupervised learning of object landmarks by factorized spatial embeddings. In: Proceedings of ICCV (2017)
33.
Zurück zum Zitat Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499–1503 (2016)CrossRef Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499–1503 (2016)CrossRef
34.
Zurück zum Zitat Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs/1412.6980 (2014) Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs/1412.6980 (2014)
35.
Zurück zum Zitat Klare, B.F., Klein, B., Taborsky, E., Blanton, A., Cheney, J., Allen, K., Grother, P., Mah, A., Jain, A.K.: Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A. In: Proceedings of CVPR (2015) Klare, B.F., Klein, B., Taborsky, E., Blanton, A., Cheney, J., Allen, K., Grother, P., Mah, A., Jain, A.K.: Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A. In: Proceedings of CVPR (2015)
36.
Zurück zum Zitat Navaneeth, B., Jingxiao, Z., Hongyu, X., Jun-Cheng, C., Carlos, C., Rama, C.: Deep heterogeneous feature fusion for template-based face recognition. In: IEEE Winter Conference on Applications of Computer Vision, WACV (2017) Navaneeth, B., Jingxiao, Z., Hongyu, X., Jun-Cheng, C., Carlos, C., Rama, C.: Deep heterogeneous feature fusion for template-based face recognition. In: IEEE Winter Conference on Applications of Computer Vision, WACV (2017)
Metadaten
Titel
Comparator Networks
verfasst von
Weidi Xie
Li Shen
Andrew Zisserman
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-030-01252-6_48

Premium Partner