Convolutional Models for Joint Object Categorization and Pose Estimation

Abstract

In the task of Object Recognition, there exists a dichotomy between the categorization of objects and estimating object pose, where the former necessitates a view-invariant representation, while the latter requires a representation capable of capturing pose information over different categories of objects. With the rise of deep architectures, the prime focus has been on object category recognition. Deep learning methods have achieved wide success in this task. In contrast, object pose regression using these approaches has received relatively much less attention. In this paper we show how deep architectures, specifically Convolutional Neural Networks (CNN), can be adapted to the task of simultaneous categorization and pose estimation of objects. We investigate and analyze the layers of various CNN models and extensively compare between them with the goal of discovering how the layers of distributed representations of CNNs represent object pose information and how this contradicts with object category representations. We extensively experiment on two recent large and challenging multi-view datasets. Our models achieve better than state-of-the-art performance on both datasets.

only for workshop presentation at ICLR

References in corpus (8)

• Return of the Devil in the Details: Delving Deep into Convolutional Nets
• R-CNNs for Pose Estimation and Action Detection
• Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network
• Viewpoints and Keypoints
• What is Holding Back Convnets for Detection?
• Digging Deep into the layers of CNNs: In Search of How CNNs Achieve View Invariance
• 3D Object Class Detection in the Wild
• Factorization of View-Object Manifolds for Joint Object Recognition and Pose Estimation

Cited by in corpus (5)

• Unified Perceptual Parsing for Scene Understanding
• Digging Deep into the layers of CNNs: In Search of How CNNs Achieve View Invariance
• Hybrid Bayesian Eigenobjects: Combining Linear Subspace and Deep Network Methods for 3D Robot Vision
• What can we learn about CNNs from a large scale controlled object dataset?
• Unified Representation Learning for Efficient Medical Image Analysis