Deep Supervision with Intermediate Concepts (BayLearn)

Publication Date: 10/11/2018

Event: BayLearn Symposium 2018, Menlo Park, CA USA

Reference: pp 1-3, 2018

Authors: Chi Li, Johns Hopkins University, NEC Laboratories America, Inc.; M. Zeeshan Zia, NEC Laboratories America, Inc.; Quoc-Huy Tran, NEC Laboratories America, Inc.; Xiang Yu, NEC Laboratories America, Inc.; Gregory Hager, Johns Hopkins University; Manmohan Chandraker, NEC Laboratories America, Inc.

Abstract: We introduce a novel technique for training convolutional neural networks (CNNs), namely deep supervision with intermediate concepts, leading to improved generalization. Our approach draws inspiration from Deeply Supervised Nets (DSN) [5], which supervises each layer by the main task to accelerate training convergence. Our method differs from DSN in that we apply deep supervision with intermediate concepts, intrinsic to the ultimate task, to regularize the network for better generalization. We apply this improved generalization ability to transfer knowledge from synthetic to real images.

Publication Link: