Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Factors of Transferability for a Generic ConvNet Representation
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP. (Computer Vision)ORCID-id: 0000-0001-5211-6388
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.ORCID-id: 0000-0002-4266-6746
Vise andre og tillknytning
2016 (engelsk)Inngår i: IEEE Transaction on Pattern Analysis and Machine Intelligence, ISSN 0162-8828, E-ISSN 1939-3539, Vol. 38, nr 9, s. 1790-1802, artikkel-id 7328311Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

Evidence is mounting that Convolutional Networks (ConvNets) are the most effective representation learning method for visual recognition tasks. In the common scenario, a ConvNet is trained on a large labeled dataset (source) and the feed-forward units activation of the trained network, at a certain layer of the network, is used as a generic representation of an input image for a task with relatively smaller training set (target). Recent studies have shown this form of representation transfer to be suitable for a wide range of target visual recognition tasks. This paper introduces and investigates several factors affecting the transferability of such representations. It includes parameters for training of the source ConvNet such as its architecture, distribution of the training data, etc. and also the parameters of feature extraction such as layer of the trained ConvNet, dimensionality reduction, etc. Then, by optimizing these factors, we show that significant improvements can be achieved on various (17) visual recognition tasks. We further show that these visual recognition tasks can be categorically ordered based on their similarity to the source task such that a correlation between the performance of tasks and their similarity to the source task w.r.t. the proposed factors is observed.

sted, utgiver, år, opplag, sider
IEEE Computer Society Digital Library, 2016. Vol. 38, nr 9, s. 1790-1802, artikkel-id 7328311
HSV kategori
Forskningsprogram
Datalogi
Identifikatorer
URN: urn:nbn:se:kth:diva-177033DOI: 10.1109/TPAMI.2015.2500224ISI: 000381432700006Scopus ID: 2-s2.0-84981266620OAI: oai:DiVA.org:kth-177033DiVA, id: diva2:870273
Merknad

QC 20161208

Tilgjengelig fra: 2015-11-13 Laget: 2015-11-13 Sist oppdatert: 2018-01-10bibliografisk kontrollert
Inngår i avhandling
1. Visual Representations and Models: From Latent SVM to Deep Learning
Åpne denne publikasjonen i ny fane eller vindu >>Visual Representations and Models: From Latent SVM to Deep Learning
2016 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
Abstract [en]

Two important components of a visual recognition system are representation and model. Both involves the selection and learning of the features that are indicative for recognition and discarding those features that are uninformative. This thesis, in its general form, proposes different techniques within the frameworks of two learning systems for representation and modeling. Namely, latent support vector machines (latent SVMs) and deep learning.

First, we propose various approaches to group the positive samples into clusters of visually similar instances. Given a fixed representation, the sampled space of the positive distribution is usually structured. The proposed clustering techniques include a novel similarity measure based on exemplar learning, an approach for using additional annotation, and augmenting latent SVM to automatically find clusters whose members can be reliably distinguished from background class. 

In another effort, a strongly supervised DPM is suggested to study how these models can benefit from privileged information. The extra information comes in the form of semantic parts annotation (i.e. their presence and location). And they are used to constrain DPMs latent variables during or prior to the optimization of the latent SVM. Its effectiveness is demonstrated on the task of animal detection.

Finally, we generalize the formulation of discriminative latent variable models, including DPMs, to incorporate new set of latent variables representing the structure or properties of negative samples. Thus, we term them as negative latent variables. We show this generalization affects state-of-the-art techniques and helps the visual recognition by explicitly searching for counter evidences of an object presence.

Following the resurgence of deep networks, in the last works of this thesis we have focused on deep learning in order to produce a generic representation for visual recognition. A Convolutional Network (ConvNet) is trained on a largely annotated image classification dataset called ImageNet with $\sim1.3$ million images. Then, the activations at each layer of the trained ConvNet can be treated as the representation of an input image. We show that such a representation is surprisingly effective for various recognition tasks, making it clearly superior to all the handcrafted features previously used in visual recognition (such as HOG in our first works on DPM). We further investigate the ways that one can improve this representation for a task in mind. We propose various factors involving before or after the training of the representation which can improve the efficacy of the ConvNet representation. These factors are analyzed on 16 datasets from various subfields of visual recognition.

sted, utgiver, år, opplag, sider
Stockholm, Sweden: KTH Royal Institute of Technology, 2016. s. 172
Serie
TRITA-CSC-A, ISSN 1653-5723 ; 21
Emneord
Computer Vision, Machine Learning, Artificial Intelligence, Deep Learning, Learning Representation, Deformable Part Models, Discriminative Latent Variable Models, Convolutional Networks, Object Recognition, Object Detection
HSV kategori
Forskningsprogram
Datalogi
Identifikatorer
urn:nbn:se:kth:diva-192289 (URN)978-91-7729-110-7 (ISBN)
Eksternt samarbeid:
Disputas
2016-09-27, Kollegiesalen, Brinellvägen 8, KTH-huset, våningsplan 4, KTH Campus, Stockholm, 15:26 (engelsk)
Opponent
Veileder
Merknad

QC 20160908

Tilgjengelig fra: 2016-09-08 Laget: 2016-09-08 Sist oppdatert: 2016-09-09bibliografisk kontrollert
2. Convolutional Network Representation for Visual Recognition
Åpne denne publikasjonen i ny fane eller vindu >>Convolutional Network Representation for Visual Recognition
2017 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
Abstract [en]

Image representation is a key component in visual recognition systems. In visual recognition problem, the solution or the model should be able to learn and infer the quality of certain visual semantics in the image. Therefore, it is important for the model to represent the input image in a way that the semantics of interest can be inferred easily and reliably. This thesis is written in the form of a compilation of publications and tries to look into the Convolutional Networks (CovnNets) representation in visual recognition problems from an empirical perspective. Convolutional Network is a special class of Neural Networks with a hierarchical structure where every layer’s output (except for the last layer) will be the input of another one. It was shown that ConvNets are powerful tools to learn a generic representation of an image. In this body of work, we first showed that this is indeed the case and ConvNet representation with a simple classifier can outperform highly-tuned pipelines based on hand-crafted features. To be precise, we first trained a ConvNet on a large dataset, then for every image in another task with a small dataset, we feedforward the image to the ConvNet and take the ConvNets activation on a certain layer as the image representation. Transferring the knowledge from the large dataset (source task) to the small dataset (target task) proved to be effective and outperformed baselines on a variety of tasks in visual recognition. We also evaluated the presence of spatial visual semantics in ConvNet representation and observed that ConvNet retains significant spatial information despite the fact that it has never been explicitly trained to preserve low-level semantics. We then tried to investigate the factors that affect the transferability of these representations. We studied various factors on a diverse set of visual recognition tasks and found a consistent correlation between the effect of those factors and the similarity of the target task to the source task. This intuition alongside the experimental results provides a guideline to improve the performance of visual recognition tasks using ConvNet features. Finally, we addressed the task of visual instance retrieval specifically as an example of how these simple intuitions can increase the performance of the target task massively.

sted, utgiver, år, opplag, sider
KTH Royal Institute of Technology, 2017. s. 130
Serie
TRITA-CSC-A, ISSN 1653-5723 ; 2017:01
Emneord
Convolutional Network, Visual Recognition, Transfer Learning
HSV kategori
Forskningsprogram
Datalogi
Identifikatorer
urn:nbn:se:kth:diva-197919 (URN)978-91-7729-213-5 (ISBN)
Disputas
2017-01-13, F3, Lindstedtsvagen 26, Stockholm, 10:00 (engelsk)
Opponent
Veileder
Merknad

QC 20161209

Tilgjengelig fra: 2016-12-09 Laget: 2016-12-09 Sist oppdatert: 2016-12-23bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopusIEEEXplore

Personposter BETA

Azizpour, HosseinMaki, Atsuto

Søk i DiVA

Av forfatter/redaktør
Azizpour, HosseinSharif Razavian, AliSullivan, JosephineMaki, AtsutoCarlssom, Stefan
Av organisasjonen
I samme tidsskrift
IEEE Transaction on Pattern Analysis and Machine Intelligence

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 702 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf