Entropy-based latent structured output prediction
Recently several generalizations of the popular latent structural SVM framework have been proposed in the literature. Broadly speaking, the generalizations can be divided into two categories: (i) those that predict the output variables while either marginalizing the latent variables or estimating th...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Published: |
Institute of Electrical and Electronics Engineers
2016
|
| _version_ | 1797100211000049664 |
|---|---|
| author | Bouchacourt, D Nowozin, S Mudigonda, P |
| author_facet | Bouchacourt, D Nowozin, S Mudigonda, P |
| author_sort | Bouchacourt, D |
| collection | OXFORD |
| description | Recently several generalizations of the popular latent structural SVM framework have been proposed in the literature. Broadly speaking, the generalizations can be divided into two categories: (i) those that predict the output variables while either marginalizing the latent variables or estimating their most likely values; and (ii) those that predict the output variables by minimizing an entropy-based uncertainty measure over the latent space. In order to aid their application in computer vision, we study these generalizations with the aim of identifying their strengths and weaknesses. To this end, we propose a novel prediction criterion that includes as special cases all previous prediction criteria that have been used in the literature. Specifically, our framework’s prediction criterion minimizes the Aczel and Daroczy entropy of the output. This in turn allows us to design a learning objective that provides a unified framework (UF) for latent structured prediction. We develop a single optimization algorithm and empirically show that it is as effective as the more complex approaches that have been previously employed for latent structured prediction. Using this algorithm, we provide empirical evidence that lends support to prediction via the minimization of the latent space uncertainty. |
| first_indexed | 2024-03-07T05:34:30Z |
| format | Conference item |
| id | oxford-uuid:e36b6566-62ab-4d57-9666-db3e9a619b51 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T05:34:30Z |
| publishDate | 2016 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | oxford-uuid:e36b6566-62ab-4d57-9666-db3e9a619b512022-03-27T10:08:59ZEntropy-based latent structured output predictionConference itemhttp://purl.org/coar/resource_type/c_5794uuid:e36b6566-62ab-4d57-9666-db3e9a619b51Symplectic Elements at OxfordInstitute of Electrical and Electronics Engineers2016Bouchacourt, DNowozin, SMudigonda, PRecently several generalizations of the popular latent structural SVM framework have been proposed in the literature. Broadly speaking, the generalizations can be divided into two categories: (i) those that predict the output variables while either marginalizing the latent variables or estimating their most likely values; and (ii) those that predict the output variables by minimizing an entropy-based uncertainty measure over the latent space. In order to aid their application in computer vision, we study these generalizations with the aim of identifying their strengths and weaknesses. To this end, we propose a novel prediction criterion that includes as special cases all previous prediction criteria that have been used in the literature. Specifically, our framework’s prediction criterion minimizes the Aczel and Daroczy entropy of the output. This in turn allows us to design a learning objective that provides a unified framework (UF) for latent structured prediction. We develop a single optimization algorithm and empirically show that it is as effective as the more complex approaches that have been previously employed for latent structured prediction. Using this algorithm, we provide empirical evidence that lends support to prediction via the minimization of the latent space uncertainty. |
| spellingShingle | Bouchacourt, D Nowozin, S Mudigonda, P Entropy-based latent structured output prediction |
| title | Entropy-based latent structured output prediction |
| title_full | Entropy-based latent structured output prediction |
| title_fullStr | Entropy-based latent structured output prediction |
| title_full_unstemmed | Entropy-based latent structured output prediction |
| title_short | Entropy-based latent structured output prediction |
| title_sort | entropy based latent structured output prediction |
| work_keys_str_mv | AT bouchacourtd entropybasedlatentstructuredoutputprediction AT nowozins entropybasedlatentstructuredoutputprediction AT mudigondap entropybasedlatentstructuredoutputprediction |