Group Norm for Learning Structured SVMs with Unstructured Latent Variables

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 overfitting 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 1 -2 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.

Generative regularization with latent topics for discriminative object recognition

“…In [11] the optimal number of mixture components is learnt using a group-sparsity inducing norm. An important difference of our 65 approach compared to these works is that we model the grouping of instances as a continuous soft-assignment instead of a discrete labeling.…”