Learning Globally-Consistent Local Distance Functions for Shape-Based Image Retrieval and Classification

Frome, Andrea; Singer, Yoram; Sha, Fei; Malik, Jitendra

doi:10.1109/iccv.2007.4408839

Cited by 293 publications

(277 citation statements)

References 16 publications

Supporting

Mentioning

276

Contrasting

Order By: Relevance

“…In some applications this was shown to be inferior to uniform weighting of the kernels (Noble, 2008). 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).…”

Section: Related Workmentioning

confidence: 99%

“…However, in all the above examples, the precise numerical value of pairwise similarity between objects is usually not available. Fortunately, one can often obtain information about the relative similarity of different pairs (Frome et al, 2007), for instance, by presenting people with several object pairs and asking them to select the pair that is most similar. For large scale data, where man-in-the-loop experiments are prohibitively costly, relative similarities can be extracted from analyzing pairs of images that are returned in response to the same text query (Schultz and Joachims, 2004).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Large Scale Online Learning of Image Similarity through Ranking

Chechik

Sharma

Shalit

et al. 2009

Lecture Notes in Computer Science

422

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

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Large Scale Online Learning of Image Similarity through Ranking

Chechik

Sharma

Shalit

et al. 2009

Lecture Notes in Computer Science

422

624

View full text Add to dashboard Cite

show abstract

“…In the second strategy, the system learns a feature space mapping (e.g., with LDA) with only those instances close to the test example [17,31], thereby tailoring the representation to the input. In a similar spirit, local metric learning methods use example-specific weights [15,25] or a cluster-specific feature transformation [32], then apply nearest neighbor classification. For all these prior methods, a test case is a new data point, and its neighboring examples are identified by nearest neighbor search (e.g., with Euclidean distance).…”

Section: Related Workmentioning

confidence: 99%

Fine-Grained Visual Comparisons with Local Learning

Grauman

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

420

302

View full text Add to dashboard Cite

Given two images, we want to predict which exhibits a particular visual attribute more than the other-even when the two images are quite similar. Existing relative attribute methods rely on global ranking functions; yet rarely will the visual cues relevant to a comparison be constant for all data, nor will humans' perception of the attribute necessarily permit a global ordering. To address these issues, we propose a local learning approach for fine-grained visual comparisons. Given a novel pair of images, we learn a local ranking model on the fly, using only analogous training comparisons. We show how to identify these analogous pairs using learned metrics. With results on three challenging datasets-including a large newly curated dataset for fine-grained comparisons-our method outperforms stateof-the-art methods for relative attribute prediction.

show abstract

“…Consider for example a content-based image retrieval setting, if the query is an image of a natural scene, color might be important but it might be less important for an indoor scene. Local learning algorithms [4,23,9,8,20] attempt to address this problem by adjusting the parameters of the model to the properties of the training set in different areas of the input space. In the transductive setting, the simplest local algorithm proceeds in two steps.…”

Section: Introductionmentioning

confidence: 99%

“…These types of constraints could be obtained from feedback of users of the retrieval system. In the standard ranking SVMs [18,1,9,8,5], one assumes that a set of elementary pair-wise similarity functions is given and uses the triplets to learn an optimal weigthed combination of these functions. In this global ranking model the same weighted combination is used for all queries independently of where they lie in the query space.…”

Section: Introductionmentioning

confidence: 99%

A Latent Variable Ranking Model for Content-Based Retrieval

Carreras

Torralba

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Since their introduction, ranking SVM models [11] have become a powerful tool for training content-based retrieval systems. All we need for training a model are retrieval examples in the form of triplet constraints, i.e. examples specifying that relative to some query, a database item a should be ranked higher than database item b. These types of constraints could be obtained from feedback of users of the retrieval system. Most previous ranking models learn either a global combination of elementary similarity functions or a combination defined with respect to a single database item. Instead, we propose a "coarse to fine" ranking model where given a query we first compute a distribution over "coarse" classes and then use the linear combination that has been optimized for queries of that class. These coarse classes are hidden and need to be induced by the training algorithm. We propose a latent variable ranking model that induces both the latent classes and the weights of the linear combination for each class from ranking triplets. Our experiments over two large image datasets and a text retrieval dataset show the advantages of our model over learning a global combination as well as a combination for each test point (i.e. transductive setting). Furthermore, compared to the transductive approach our model has a clear computational advantages since it does not need to be retrained for each test query.

show abstract

Learning Globally-Consistent Local Distance Functions for Shape-Based Image Retrieval and Classification

Cited by 293 publications

References 16 publications

Large Scale Online Learning of Image Similarity through Ranking

Large Scale Online Learning of Image Similarity through Ranking

Fine-Grained Visual Comparisons with Local Learning

A Latent Variable Ranking Model for Content-Based Retrieval

Contact Info

Product

Resources

About