Deep Supervision with Intermediate Concepts

Chi Li, M. Zeeshan Zia, Quoc Huy Tran, Xiang Yu, Gregory Hager, Manmohan Chandraker

Research output: Contribution to journalArticle


Recent data-driven approaches to scene interpretation predominantly pose inference as an end-to-end black-box mapping, commonly performed by a Convolutional Neural Network (CNN). However, decades of work on perceptual organization in both human and machine vision suggest that there are often intermediate representations that are intrinsic to an inference task, and which provide essential structure to improve generalization. In this work, we explore an approach for injecting prior domain structure into neural network training by supervising hidden layers of a CNN with intermediate concepts that normally are not observed in practice. We formulate a probabilistic framework which formalizes these notions and predicts improved generalization via this deep supervision method. One advantage of this approach is that we are able to train only from synthetic CAD renderings of cluttered scenes, where concept values can be extracted, but apply the results to real images. Our implementation achieves the state-of-the-art performance of 2D/3D keypoint localization and image classification on real image benchmarks including KITTI, PASCAL VOC, PASCAL3D+, IKEA, and CIFAR100. We provide additional evidence that our approach outperforms alternative forms of supervision, such as multi-task networks.

Original languageEnglish (US)
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
StateAccepted/In press - Aug 10 2018


  • Deep learning
  • multi-task learning
  • object pose estimation
  • Rendering (computer graphics)
  • Shape
  • single image 3D structure prediction
  • Solid modeling
  • Task analysis
  • Three-dimensional displays
  • Training data
  • Two dimensional displays

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Deep Supervision with Intermediate Concepts'. Together they form a unique fingerprint.

  • Cite this