Dimensionality Reduction by Learning an Invariant Mapping

Hadsell, Raia; Chopra, Sumit; LeCun, Yann

doi:10.1109/cvpr.2006.100

Cited by 3,913 publications

(2,976 citation statements)

References 10 publications

Supporting

Mentioning

2,796

Contrasting

Unclassified

Order By: Relevance

“…MDS has been applied to many natural categories, including Morse code (Rothkopf, 1957) and colors (Nosofsky, 1987). Traditional MDS does not scale well to a large number of objects because all pairwise judgments must be collected, but alternative formulations have been developed to deal with large numbers of stimuli (Hadsell, Chopra, & LeCun, 2006;de Silva & Tenenbaum, 2003;Goldstone, 1994).…”

Section: Methods For Studying Categoriesmentioning

confidence: 99%

“…Classical MDS is most commonly applied MDS method in psychological experiments, but it was impractical in this situation because a very large number of pairwise similarity judgments would have been needed to construct a scaling solution for the MCMC samples. Instead, an MDS variant known as Dimensionality Reduction by Learning an Invariant Mapping (DrLIM; Hadsell et al, 2006) was used. DrLIM has not been used in psychological experiments to our knowledge, but was chosen because its advantages over classical MDS.…”

Section: Methodsmentioning

confidence: 99%

“…Research in dimensionality reduction has produced many different algorithmic approaches to this problem and these approaches can produce different solutions (Hadsell et al, 2006;Hinton & Salkhutdinov, 2006;Roweis & Saul, 2000;Tenenbaum, de Silva, & Langford, 2000). In order to make strong claims about models it will be important for the neighborhood judgments to lead to consistent representations under a variety of plausible assumptions.…”

Section: Non-neighbors Only Impact the Loss Function Within A Certainmentioning

confidence: 99%

See 2 more Smart Citations

Uncovering mental representations with Markov chain Monte Carlo

Sanborn

Griffiths

Shiffrin

2010

Cognitive Psychology

View full text Add to dashboard Cite

A note on versions:The version presented here may differ from the published version or, version of record, if you wish to cite this item you are advised to consult the publisher's version. Please see the 'permanent WRAP URL' above for details on accessing the published version and note that access may require a subscription. Richard M. Shiffrin Indiana University, Bloomington Abstract A key challenge for cognitive psychology is the investigation of mental representations, such as object categories, subjective probabilities, choice utilities, and memory traces. In many cases, these representations can be expressed as a non-negative function defined over a set of objects. We present a behavioral method for estimating these functions. Our approach uses people as components of a Markov chain Monte Carlo (MCMC) algorithm, a sophisticated sampling method originally developed in statistical physics. Experiments 1 and 2 verified the MCMC method by training participants on various category structures and then recovering those structures. Experiment 3 demonstrated that the MCMC method can be used estimate the structures of the real-world animal shape categories of giraffes, horses, dogs, and cats. Experiment 4 combined the MCMC method with multidimensional scaling to demonstrate how different accounts of the structure of categories, such as prototype and exemplar models, can be tested, producing samples from the categories of apples, oranges, and grapes.

show abstract

Section: Methods For Studying Categoriesmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Non-neighbors Only Impact the Loss Function Within A Certainmentioning

confidence: 99%

See 1 more Smart Citation

Uncovering mental representations with Markov chain Monte Carlo

Sanborn

Griffiths

Shiffrin

2010

Cognitive Psychology

View full text Add to dashboard Cite

show abstract

“…The work of Frome et al (2007) further learns a weighting over local distance function for every image in the training set. Non linear image similarity learning was also studied in the context of dimensionality reduction, as in Hadsell et al (2006). Finally, Jain et al (2008a,b), based on work by Davis et al (2007), aim to learn metrics in an online setting.…”

Section: Related Workmentioning

confidence: 99%

Large Scale Online Learning of Image Similarity through Ranking

Chechik

Sharma

Shalit

et al. 2009

Lecture Notes in Computer Science

417

624

View full text Add to dashboard Cite

Learning a measure of similarity between pairs of objects is an important generic problem in machine learning. It is particularly useful in large scale applications like searching for an image that is similar to a given image or finding videos that are relevant to a given video. In these tasks, users look for objects that are not only visually similar but also semantically related to a given object. Unfortunately, the approaches that exist today for learning such semantic similarity do not scale to large datasets. This is both because typically their CPU and storage requirements grow quadratically with the sample size, and because many methods impose complex positivity constraints on the space of learned similarity functions.The current paper presents OASIS, an Online Algorithm for Scalable Image Similarity learning that learns a bilinear similarity measure over sparse representations. OASIS is an online dual approach using the passive-aggressive family of learning algorithms with a large margin criterion and an efficient hinge loss cost. Our experiments show that OASIS is both fast and accurate at a wide range of scales: for a dataset with thousands of images, it achieves better results than existing state-of-the-art methods, while being an order of magnitude faster. For large, web scale, datasets, OASIS can be trained on more than two million images from 150K text queries within 3 days on a single CPU. On this large scale dataset, human evaluations showed that 35% of the ten nearest neighbors of a given test image, as found by OASIS, were semantically relevant to that image. This suggests that query independent similarity could be accurately learned even for large scale datasets that could not be handled before.

show abstract

“…Siamese network [23] , learning the direct mapping from original images to a feature space in which images from the identical person are approached while images from disparate person are widely separated. [27] Propose a "Siamese" convolutional network for metric learning.…”

Section: Scale Invariant Local Ternary Pattern (Siltp)mentioning

confidence: 99%

A Study on Person Re-Identification System using Enhanced RNN

Choi¹,

Xu²

2017

JIIBC

View full text Add to dashboard Cite

The person Re-identification is the most challenging part of computer vision due to the significant changes in human pose and background clutter with occlusions. The picture from non-overlapping cameras enhance the difficulty to distinguish some person from the other. To reach a better performance match, most methods use feature selection and distance metrics separately to get discriminative representations and proper distance to describe the similarity between person and kind of ignoring some significant features. This situation has encouraged us to consider a novel method to deal with this problem. In this paper, we proposed an enhanced recurrent neural network with three-tier hierarchical network for person re-identification. Specifically, the proposed recurrent neural network (RNN) model contain an iterative expectation maximum (EM) algorithm and three-tier Hierarchical network to jointly learn both the discriminative features and metrics distance. The iterative EM algorithm can fully use of the feature extraction ability of convolutional neural network (CNN) which is in series before the RNN. By unsupervised learning, the EM framework can change the labels of the patches and train larger datasets. Through the three-tier hierarchical network, the convolutional neural network, recurrent network and pooling layer can jointly be a feature extractor to better train the network. The experimental result shows that comparing with other researchers' approaches in this field, this method also can get a competitive accuracy. The influence of different component of this method will be analyzed and evaluated in the future research.

show abstract

Dimensionality Reduction by Learning an Invariant Mapping

Cited by 3,913 publications

References 10 publications

Uncovering mental representations with Markov chain Monte Carlo

Uncovering mental representations with Markov chain Monte Carlo

Large Scale Online Learning of Image Similarity through Ranking

A Study on Person Re-Identification System using Enhanced RNN

Contact Info

Product

Resources

About