BranchConnect: Image Categorization with Learned Branch Connections

By Karim Ahmed, Lorenzo Torresani. 2017

5 citations recorded by the source corpus.

We introduce an architecture for image categorization that enables the end-to-end learning of separate visual features for the different classes to distinguish. The proposed model consists of a deep CNN shaped like a tree. The stem of the tree includes a sequence of convolutional layers common to all classes. The stem then splits into multiple branches implementing parallel feature extractors, which are ultimately connected to the final classification layer via learned gated connections. These learned gates determine for each individual class the subset of features to use. Such a scheme naturally encourages the learning of a heterogeneous set of specialized features through the separate branches and it allows each class to use the subset of features that are optimal for its recognition. We show the generality of our proposed method by reshaping several popular CNNs from the literature into our proposed architecture. Our experiments on the CIFAR100, CIFAR10, ImageNet, and Synth datasets show that in each case our resulting model yields a substantial improvement in accuracy over the original CNN. Our empirical analysis also suggests that our scheme acts as a form of beneficial regularization improving generalization performance.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Peter Hase
  2. Cynthia Rudin
  3. Oscar Li
  4. Mohit Bansal
  5. Berk Ustun
  6. Tong Wang
  7. Octavio Loyola-González
  8. Zhi Chen

In Computer Vision and Pattern Recognition

  1. Cynthia Rudin
  2. Peter Hase
  3. Oscar Li

Citations in the corpus