Name
Abstract | ||
|---|---|---|
Latent variables models have been applied to a number of computer vision problems. However, the complexity of the latent space is typically left as a free design choice. A larger latent space results in a more expressive model, but such models are prone to over fitting and are slower to perform inference with. The goal of this paper is to regularize the complexity of the latent space and learn which hidden states are really relevant for prediction. Specifically, we propose using group-sparsity-inducing regularizers such as l1-l2 to estimate the parameters of Structured SVMs with unstructured latent variables. Our experiments on digit recognition and object detection show that our approach is indeed able to control the complexity of latent space without any significant loss in accuracy of the learnt model. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/ICCV.2013.58 | ICCV |
Keywords | Field | DocType |
learnt model,larger latent space result,group norm,latent space,structured svms,unstructured latent variables,digit recognition,detection show,learning structured svms,latent variables model,computer vision problem,expressive model,unstructured latent variable,learning artificial intelligence,support vector machines,computer vision | Object detection,Pattern recognition,Computer science,Inference,Support vector machine,Latent class model,Latent variable,Probabilistic latent semantic analysis,Artificial intelligence,Coordinate descent,Overfitting,Machine learning | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1550-5499 |
Citations | PageRank | References |
4 | 0.38 | 18 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Daozheng Chen | 1 | 73 | 5.05 |
| Dhruv Batra | 2 | 2142 | 104.81 |
| William T. Freeman | 3 | 17382 | 1968.76 |