Discriminative Training of Hyper-feature Models for Object Identification

Jain, Virendra; Ferencz, Andras; Learned-Miller, Erik

doi:10.5244/c.20.37

Cited by 22 publications

(29 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently there has been considerable interest for face and visual identification [5,8,12,15,20,24]. Faces are particularly challenging due to possible variations in appearance, see for example Figure 1.…”

Section: Introductionmentioning

confidence: 99%

Is that you? Metric learning approaches for face identification

Guillaumin

Verbeek

Schmid

2009

2009 IEEE 12th International Conference on Computer Vision

676

613

View full text Add to dashboard Cite

Face identification is the problem of determining whether two face images depict the same person or not. This is difficult due to variations in scale, pose, lighting, background, expression, hairstyle, and glasses. In this paper we present two methods for learning robust distance measures: (a) a logistic discriminant approach which learns the metric from a set of labelled image pairs (LDML) and (b) a nearest neighbour approach which computes the probability for two images to belong to the same class (MkNN). We evaluate our approaches on the Labeled Faces in the Wild data set, a large and very challenging data set of faces from Yahoo! News. The evaluation protocol for this data set defines a restricted setting, where a fixed set of positive and negative image pairs is given, as well as an unrestricted one, where faces are labelled by their identity. We are the first to present results for the unrestricted setting, and show that our methods benefit from this richer training data, much more so than the current state-of-the-art method. Our results of 79.3% and 87.5% correct for the restricted and unrestricted setting respectively, significantly improve over the current state-of-the-art result of 78.5%. Confidence scores obtained for face identification can be used for many applications e.g. clustering or recognition from a single training example. We show that our learned metrics also improve performance for these tasks.

show abstract

Section: Introductionmentioning

confidence: 99%

Is that you? Metric learning approaches for face identification

Guillaumin

Verbeek

Schmid

2009

2009 IEEE 12th International Conference on Computer Vision

676

613

View full text Add to dashboard Cite

show abstract

“…The toy cars dataset The Jain faces dataset [12] is a subset of "Faces in the news" 2 and contains 500 positive and 500 negative pairs of faces, and we measure our accuracy like the authors by 10 fold cross validation. That dataset is built from faces sampled "in the news", hence there are very large differences of resolution, light, appearance, expression, pose, noise, etc.…”

Section: Resultsmentioning

confidence: 99%

Learning Visual Similarity Measures for Comparing Never Seen Objects

Nowak

Jurie

2007

2007 IEEE Conference on Computer Vision and Pattern Recognition

135

111

View full text Add to dashboard Cite

In this paper we propose and evaluate an algorithm that learns a similarity measure for comparing never seen objects. The measure is learned from pairs of training images labeled "same" or "different". This is far less informative than the commonly used individual image labels (e.g. "car model X"), but it is cheaper to obtain. The proposed algorithm learns the characteristic differences between local descriptors sampled from pairs of "same" and "different" images. These differences are vector quantized by an ensemble of extremely randomized binary trees, and the similarity measure is computed from the quantized differences. The extremely randomized trees are fast to learn, robust due to the redundant information they carry and they have been proved to be very good clusterers. Furthermore, the trees efficiently combine different feature types (SIFT and geometry). We evaluate our innovative similarity measure on four very different datasets and consistantly outperform the state-of-the-art competitive approaches.

show abstract

“…Finally, the magenta X at 4.3 patches and 1.02% error shows the performance of the cascade model ample classification results. As part of an extension of this current paper (Jain et al 2006), we have also compared this algorithm to Bayesian face recognition (Moghaddam et al 2000), which won the 1996 FERET face identification competition, and found our algorithm to perform significantly better on this difficult data set. Our more recent work further improves on the results reported here by training a discriminative model on top of the hyper-features.…”

Section: Facesmentioning

confidence: 99%

Learning to Locate Informative Features for Visual Identification

Ferencz¹,

Learned-Miller

Malik

2007

Int J Comput Vis

View full text Add to dashboard Cite

Object identification is a specialized type of recognition in which the category (e.g. cars) is known and the goal is to recognize an object's exact identity (e.g. Bob's BMW). Two special challenges characterize object identification. First, inter-object variation is often small (many cars look alike) and may be dwarfed by illumination or pose changes. Second, there may be many different instances of the category but few or just one positive "training" examples per object instance. Because variation among object instances may be small, a solution must locate possibly subtle object-specific salient features, like a door handle, while avoiding distracting ones such as specular highlights. With just one training example per object instance, however, standard modeling and feature selection techniques cannot be used. We describe an on-line algorithm that takes one image from a known category and builds an efficient "same" versus "different" classification cascade by predicting the most discriminative features for that object instance. Our method not only estimates the saliency and scoring function for each candidate feature, but also models the dependency between features, building an ordered sequence of discriminative features specific to the given image. Learned stopping thresholds make the identifier very efficient. To make this possible, category-specific characteristics are learned automatically in an off-line training procedure from labeled image pairs of the category. Our method, using the same algorithm for both cars and faces, outperforms a wide variety of other methods.

show abstract

Discriminative Training of Hyper-feature Models for Object Identification

Cited by 22 publications

References 15 publications

Is that you? Metric learning approaches for face identification

Is that you? Metric learning approaches for face identification

Learning Visual Similarity Measures for Comparing Never Seen Objects

Learning to Locate Informative Features for Visual Identification

Contact Info

Product

Resources

About