Yongxi Lu

Learn More
State-of-the-art object detection systems rely on an accurate set of region proposals. Several recent methods use a neural network architecture to hypothesize promising object locations. While these approaches are computation-ally efficient, they rely on fixed image regions as anchors for predictions. In this paper we propose to use a search strategy that(More)
Multi-task learning aims to improve generalization performance of multiple prediction tasks by appropriately sharing relevant information across them. In the context of deep neural networks, this idea is often realized by hand-designed network architectures with layers that are shared across tasks and branches that encode task-specific features. However,(More)
Feature pooling layers (e.g., max pooling) in convolu-tional neural networks (CNNs) serve the dual purpose of providing increasingly abstract representations as well as yielding computational savings in subsequent convo-lutional layers. We view the pooling operation in CNNs as a two-step procedure: first, a pooling window (e.g., 2 ˆ 2) slides over the(More)
  • 1