DeepAI AI Chat
Log In Sign Up

Deep Supervision with Intermediate Concepts

by   Chi Li, et al.

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 suggests 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.


page 1

page 3

page 7

page 12

page 14


Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing

Monocular 3D object parsing is highly desirable in various scenarios inc...

A Disentangling Invertible Interpretation Network for Explaining Latent Representations

Neural networks have greatly boosted performance in computer vision by l...

Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization

The generalization capability of neural networks across domains is cruci...

Progressive Scene Text Erasing with Self-Supervision

Scene text erasing seeks to erase text contents from scene images and cu...

A Comprehensive Review on Deep Supervision: Theories and Applications

Deep supervision, or known as 'intermediate supervision' or 'auxiliary s...

Structural Prior Driven Regularized Deep Learning for Sonar Image Classification

Deep learning has been recently shown to improve performance in the doma...

SPARLING: Learning Latent Representations with Extremely Sparse Activations

Real-world processes often contain intermediate state that can be modele...