Attribute Discovery via Predictable Discriminative Binary Codes

Rastegari, Mohammad; Farhadi, Ali; Forsyth, David

doi:10.1007/978-3-642-33783-3_63

Cited by 144 publications

(164 citation statements)

References 23 publications

Supporting

Mentioning

161

Contrasting

Order By: Relevance

“…For example, by including learned non-semantic attributes for better discrimination [19,25], or to learn an attribute embedding specific for zero-shot prediction [1]. Instead of relying on a predefined mapping, in [21], linguistic knowledge databases and web search hit counts are used to automatically obtain the attribute-to-class mapping.…”

Section: Related Workmentioning

confidence: 99%

COSTA: Co-Occurrence Statistics for Zero-Shot Classification

Mensink

Gavves

Snoek

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

183

184

View full text Add to dashboard Cite

In this paper we aim for zero-shot classification, that is visual recognition of an unseen class by using knowledge transfer from known classes. Our main contribution is COSTA, which exploits co-occurrences of visual concepts in images for knowledge transfer. These inter-dependencies arise naturally between concepts, and are easy to obtain from existing annotations or web-search hit counts. We estimate a classifier for a new label, as a weighted combination of related classes, using the co-occurrences to define the weight. We propose various metrics to leverage these cooccurrences, and a regression model for learning a weight for each related class. We also show that our zero-shot classifiers can serve as priors for few-shot learning. Experiments on three multi-labeled datasets reveal that our proposed zero-shot methods, are approaching and occasionally outperforming fully supervised SVMs. We conclude that cooccurrence statistics suffice for zero-shot classification.

show abstract

Section: Related Workmentioning

confidence: 99%

COSTA: Co-Occurrence Statistics for Zero-Shot Classification

Mensink

Gavves

Snoek

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

183

184

View full text Add to dashboard Cite

show abstract

“…The vocabulary of attributes can be pre-defined or it can be discovered [27,28]. Recently, attributes have been used as a mode of communication between humans and machines [17,19,20].…”

Section: Contributionsmentioning

confidence: 99%

Interactively Guiding Semi-Supervised Clustering via Attribute-Based Explanations

Lad

Parikh

2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

(ABSTRACT)Unsupervised image clustering is a challenging and often ill-posed problem. Existing image descriptors fail to capture the clustering criterion well, and more importantly, the criterion itself may depend on (unknown) user preferences. Semi-supervised approaches such as distance metric learning and constrained clustering thus leverage user-provided annotations indicating which pairs of images belong to the same cluster (must-link) and which ones do not (cannot-link). These approaches require many such constraints before achieving good clustering performance because each constraint only provides weak cues about the desired clustering.In this work, we propose to use image attributes as a modality for the user to provide more informative cues. In particular, the clustering algorithm iteratively and actively queries a user with an image pair. Instead of the user simply providing a must-link/cannot-link constraint for the pair, the user also provides an attribute-based reasoning e.g. "these two images are similar because both are natural and have still water" or "these two people are dissimilar because one is way older than the other". Under the guidance of this explanation, and equipped with attribute predictors, many additional constraints are automatically generated.We demonstrate the effectiveness of our approach by incorporating the proposed attributebased explanations in three standard semi-supervised clustering algorithms: Constrained K-Means, MPCK-Means, and Spectral Clustering, on three domains: scenes, shoes, and faces, using both binary and relative attributes.

show abstract

“…One might learn a mapping that preserves correlations between semantic similarities and binary codes [13], or local similarities [4,20,5]. Recently, discriminative binary codes have shown promising results in mapping images to a binary space where linear classifiers can perform even better than sophisticated models [11]. We use this mapping to project images to a binary space where computing simple geometric measures like compactness or diameters of a group of images and their margins from other images is very efficient.…”

Section: Related Workmentioning

confidence: 99%

Multi-attribute Queries: To Merge or Not to Merge?

Rastegari

Diba

Parikh

et al. 2013

2013 IEEE Conference on Computer Vision and Pattern Recognition

Self Cite

View full text Add to dashboard Cite

Users often have very specific visual content in mind that they are searching for. The most natural way to communicate this content to an image search engine is to use keywords that specify various properties or attributes of the content. A naive way of dealing with such multi-attribute queries is the following: train a classifier for each attribute independently, and then combine their scores on images to judge their fit to the query. We argue that this may not be the most effective or efficient approach. Conjunctions of attribute often correspond to very characteristic appearances. It would thus be beneficial to train classifiers that detect these conjunctions as a whole. But not all conjunctions result in such tight appearance clusters. So given a multi-attribute query, which conjunctions should we model? An exhaustive evaluation of all possible conjunctions would be time consuming. Hence we propose an optimization approach that identifies beneficial conjunctions without explicitly training the corresponding classifier. It reasons about geometric quantities that capture notions similar to intra-and inter-class variances. We exploit a discriminative binary space to compute these geometric quantities efficiently. Experimental results on two challenging datasets of objects and birds show that our proposed approach can improve performance significantly over several strong baselines, while being an order of magnitude faster than exhaustively searching through all possible conjunctions.

show abstract

Attribute Discovery via Predictable Discriminative Binary Codes

Cited by 144 publications

References 23 publications

COSTA: Co-Occurrence Statistics for Zero-Shot Classification

COSTA: Co-Occurrence Statistics for Zero-Shot Classification

Interactively Guiding Semi-Supervised Clustering via Attribute-Based Explanations

Multi-attribute Queries: To Merge or Not to Merge?

Contact Info

Product

Resources

About