Ändra sökning
Avgränsa sökresultatet
1 - 11 av 11
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Träffar per sida
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
Markera
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 1.
    Yang, Zhong
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Li, Vladimir
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Okada, Ryuzo
    Maki, Atsuto
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Target aware network adaptation for efficient representation learning2018Ingår i: ECCV 2018: Computer Vision – ECCV 2018 Workshops, Munich: Springer, 2018, Vol. 11132, s. 450-467Konferensbidrag (Refereegranskat)
    Abstract [en]

    This paper presents an automatic network adaptation method that finds a ConvNet structure well-suited to a given target task, e.g. image classification, for efficiency as well as accuracy in transfer learning. We call the concept target-aware transfer learning. Given only small-scale labeled data, and starting from an ImageNet pre-trained network, we exploit a scheme of removing its potential redundancy for the target task through iterative operations of filter-wise pruning and network optimization. The basic motivation is that compact networks are on one hand more efficient and should also be more tolerant, being less complex, against the risk of overfitting which would hinder the generalization of learned representations in the context of transfer learning. Further, unlike existing methods involving network simplification, we also let the scheme identify redundant portions across the entire network, which automatically results in a network structure adapted to the task at hand. We achieve this with a few novel ideas: (i) cumulative sum of activation statistics for each layer, and (ii) a priority evaluation of pruning across multiple layers. Experimental results by the method on five datasets (Flower102, CUB200-2011, Dog120, MIT67, and Stanford40) show favorable accuracies over the related state-of-the-art techniques while enhancing the computational and storage efficiency of the transferred model.

  • 2.
    Zhong, Yang
    KTH, Skolan för datavetenskap och kommunikation (CSC).
    Human Face Identification and Face Attribute Prediction: From Gabor Filtering to Deep Learning2016Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
    Abstract [en]

    After decades of research, it is exciting to see that face recognition technology has entered a most flourishing era. Driven by the latest development in data science and especially technical evolutions in computer vision and pattern recognition, face recognition has achieved significant progress over the last three years. In the near future, people can expect many useful and interesting face recognition applications to be deployed in many situations: they can be used for identifying suspects, organizing your photos with family and friends, and making computers better understand human beings. Many mysterious face recognition tricks depicted in movies may become reality in several years' time.

    This thesis focuses on the development of face recognition algorithms that identify people from a single still image. Two questions are specifically studied. First, it introduces how we identify faces captured in controlled scenarios with cooperative users. In this scenario, a face recognition system captures a face and finds the most similar face from the ones stored in the face recognition system. Second, it describes our solutions for predicting face attributes from faces captured under arbitrary imaging conditions. These two problems were tackled by different schools of technologies: the solution to the first question employed a learning-free approach, whereas the latter question was solved by using the most recent Deep Learning technology. Thus, this thesis also reflects the technological evolution of face recognition over recent years.

    To identify faces in controlled scenarios, we propose a novel Block Matching approach, which can effectively match faces without feature engineering or any machine learning components. By representing faces with very concise Gabor phase codes and matching them through our Block Matching approach, the identification accuracy is entirely comparable to and even better than the state-of-the-art. For predicting the attributes from faces captured in the wild, we propose leveraging the off-the-shelf mid-level representations from pre-trained convolutional neural networks. Comparative experiments show that our solution outperforms the previous state-of-the-art solution with a large margin in terms of both accuracy and efficiency. 

    The approaches described in this thesis may look different from the ``mainstream''. But, together with the empirical findings, I hope they could provide some insights and update widely adopted concepts for solving related face recognition and computer vision problems.

  • 3.
    Zhong, Yang
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Hedman, Anders
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Li, Haibo
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    How Good Can a Face Identifier Be Without Learning2016Ingår i: Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Constructing discriminative features is an essential issue in developing face recognition algorithms. There are two schools in how features are constructed: hand-crafted features and learned features from data. A clear trend in the face recognition community is to use learned features to replace hand-crafted ones for face recognition, due to the superb performance achieved by learned features through Deep Learning networks. Given the negative aspects of database-dependent solutions, we consider an alternative and demonstrate that, for good generalization performance, developing face recognition algorithms by using handcrafted features is surprisingly promising when the training dataset is small or medium sized. We show how to build such a face identifier with our Block Matching method which leverages the power of the Gabor phase in face images. Although no learning process is involved, empirical results show that the performance of this “designed” identifier is comparable (superior) to state-of-the-art identifiers and even close to Deep Learning approaches.

  • 4.
    Zhong, Yang
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Hedman, Anders
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Li, Haibo
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    How good can a face identifier be without learning?2017Ingår i: 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2016, Springer, 2017, Vol. 693, s. 515-533Konferensbidrag (Refereegranskat)
    Abstract [en]

    Constructing discriminative features is an essential issue in developing face recognition algorithms. There are two schools in how features are constructed: hand-crafted features and learned features from data. A clear trend in the face recognition community is to use learned features to replace hand-crafted ones for face recognition, due to the superb performance achieved by learned features through Deep Learning networks. Given the negative aspects of database-dependent solutions, we consider an alternative and demonstrate that, for good generalization performance, developing face recognition algorithms by using hand-crafted features is surprisingly promising when the training dataset is small or medium sized. We show how to build such a face identifier with our Block Matching method which leverages the power of the Gabor phase in face images. Although no learning process is involved, empirical results show that the performance of this “designed” identifier is comparable (superior) to state-of-the-art identifiers and even close to Deep Learning approaches.

  • 5. Zhong, Yang
    et al.
    Li, Haibo
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Is block matching an alternative tool to LBP for face recognition?2014Konferensbidrag (Refereegranskat)
    Abstract [en]

    In this paper, we introduce the Block Matching (BM) as an alternative patch-based local matching approach for solving the face recognition problem. The Block Matching enables an image patch of the probe face image to search for its best matching from displaced positions in the gallery face image. This matching strategy is very effective for handling spatial shift between two images and it is radically different from that of the widely used LBP type patch-based local matching approaches. Our evaluations on the FERET and CMU-PIE databases show that the performance of this simple method is well comparable (superior) to that of the popular LBP approach. We argue that the Block Matching could provide face recognition a new approach with more flexible algorithm architecture. One can expect that it could lead to much higher performance when combining with other feature extraction techniques, like Gabor wavelet and deep learning.

  • 6. Zhong, Yang
    et al.
    Li, Haibo
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Människocentrerad teknologi, Medieteknik och interaktionsdesign, MID.
    IS BLOCK MATCHING AN ALTERNATIVE TOOL TO LBP FOR FACE RECOGNITION?2014Ingår i: 2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), IEEE, 2014, s. 723-727Konferensbidrag (Refereegranskat)
    Abstract [en]

    In this paper, we introduce the Block Matching (BM) as an alternative patch-based local matching approach for solving the face recognition problem. The Block Matching enables an image patch of the probe face image to search for its best matching from displaced positions in the gallery face image. This matching strategy is very effective for handling spatial shift between two images and it is radically different from that of the widely used LBP type patch-based local matching approaches. Our evaluations on the FERET and CMU-PIE databases show that the performance of this simple method is well comparable (superior) to that of the popular LBP approach. We argue that the Block Matching could provide face recognition a new approach with more flexible algorithm architecture. One can expect that it could lead to much higher performance when combining with other feature extraction techniques, like Gabor wavelet and deep learning.

  • 7.
    Zhong, Yang
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Li, Haibo
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Leveraging Gabor Phase for Face Identification in Controlled Scenarios2016Ingår i: Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Science and Technology Publications,Lda , 2016, s. 49-58Konferensbidrag (Refereegranskat)
    Abstract [en]

    Gabor features have been widely employed in solving face recognition problems in controlled scenarios. To construct discriminative face features from the complex Gabor space, the amplitude information is commonly preferred, while the other one — the phase — is not well utilized due to its spatial shift sensitivity. In this paper, we address the problem of face recognition in controlled scenarios. Our focus is on the selection of a suitable signal representation and the development of a better strategy for face feature construction. We demonstrate that through our Block Matching scheme Gabor phase information is powerful enough to improve the performance of face identification. Compared to state of the art Gabor filtering based approaches, the proposed algorithm features much lower algorithmic complexity. This is mainly due to our Block Matching enables the employment of high definition Gabor phase. Thus, a single-scale Gabor frequency band is sufficient for discrimination. Furthermore, learning process is not involved in the facial feature construction, which avoids the risk of building a database-dependent algorithm. Benchmark evaluations show that the proposed learning-free algorith outperforms state-of-the-art Gabor approaches and is even comparable to Deep Learning solutions.

  • 8.
    Zhong, Yang
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Sullivan, Josephine
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Li, Haibo
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Face Attribute Prediction Using Off-The-Shelf CNN Features2016Ingår i: 2016 International Conference on Biometrics, ICB 2016, Institute of Electrical and Electronics Engineers (IEEE), 2016, artikel-id 7550092Konferensbidrag (Refereegranskat)
    Abstract [en]

    Predicting attributes from face images in the wild is a challenging computer vision problem. To automatically describe face attributes from face containing images, traditionally one needs to cascade three technical blocks — face localization, facial descriptor construction, and attribute classification — in a pipeline. As a typical classification problem, face attribute preiction has been addressed using deep learning. Current state-of-the-art performance was achieved by using two cascaded Convolutional Neural Networks (CNNs), which were specifically trained to learn face localization and attribute description. In this paper, we experiment with an alternative way of employing the power of deep representations from CNNs. Combining with conventional face localization techniques, we use off-the-shelf architectures trained for face recognition to build facial descriptors. Recognizing that the describable face attributes are diverse, our face descriptors are constructed from different levels of the CNNs for different attributes to best facilitate face attribute prediction. Experiments on two large datasets, LFWA and CelebA, show that our approach is entirely comparable to the state-of-the-art. Our findings not only demonstrate an efficient face attribute prediction approach, but also raise an important question: how to leverage the power of off-the-shelf CNN representations for novel tasks

  • 9.
    Zhong, Yang
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Sullivan, Josephine
    KTH, Skolan för datavetenskap och kommunikation (CSC), Robotik, perception och lärande, RPL.
    Li, Haibo
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Leveraging Mid-level Deep Representations for Prediction Face Attributes in the Wild2016Ingår i: 2016 IEEE International Conference on Image Processing (ICIP), Institute of Electrical and Electronics Engineers (IEEE), 2016Konferensbidrag (Refereegranskat)
  • 10.
    Zhong, Yang
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC).
    Sullivan, Josephine
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Li, Haibo
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Transferring from Face Recognition to Face Attribute Prediction through Adaptive Selection of Off-the-shelf CNN RepresentationsManuskript (preprint) (Övrigt vetenskapligt)
  • 11.
    Zhong, Yang
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Robotik, perception och lärande, RPL.
    Sullivan, Josephine
    KTH, Skolan för datavetenskap och kommunikation (CSC), Robotik, perception och lärande, RPL.
    Li, Haibo
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Transferring from face recognition to face attribute prediction through adaptive selection of off-the-shelf CNN representations2016Ingår i: 2016 23rd International Conference on Pattern Recognition, ICPR 2016, Institute of Electrical and Electronics Engineers (IEEE), 2016, s. 2264-2269, artikel-id 7899973Konferensbidrag (Refereegranskat)
    Abstract [en]

    This paper addresses the problem of transferring CNNs pre-trained for face recognition to a face attribute prediction task. To transfer an off-the-shelf CNN to a novel task, a typical solution is to fine-tune the network towards the novel task. As demonstrated in the state-of-the-art face attribute prediction approach, fine-tuning the high-level CNN hidden layer by using labeled attribute data leads to significant performance improvements. In this paper, however, we tackle the same problem but through a different approach. Rather than using an end-to-end network, we select face descriptors from off-the-shelf hierarchical CNN representations for recognizing different attributes. Through such an adaptive representation selection, even without any fine-tuning, our results still outperform the state-of-the-art face attribute prediction approach on the latest large-scale dataset for an error rate reduction of more than 20%. Moreover, by using intensive empirical probes, we have identified several key factors that are significant for achieving promising face attribute prediction performance. These results attempt to gain and update our understandings of the nature of CNN features and how they can be better applied to the transferred novel tasks.

1 - 11 av 11
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf