Convolutional Models for Joint Object Categorization and Pose Estimation

By Mohamed Elhoseiny, Tarek El-Gaaly, Amr Bakry, Ahmed M. Elgammal. 2015

13 citations recorded by the source corpus.

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.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Model Architectures

Citations in the corpus

Unified Perceptual Parsing for Scene Understanding (2018, background): “More recently, Elhoseiny et al. [22] have proposed a model that performs pose estimation and object classiﬁcation simultaneously.”
Deep-based Ingredient Recognition for Cooking Recipe Retrieval (2016, methodology): “In [10], multi-task DCNN models are proposed for simultaneous categorization and pose estimation of general objects (e.”
iLab-20M: A Large-Scale Controlled Object Dataset to Investigate Deep Learning (2016, methodology): “In particular, we will consider techniques such as feature embedding and loss regularization [63, 5] and joint prediction of camera parameters and object categories [13, 53].”
Digging Deep into the Layers of CNNs: In Search of How CNNs Achieve View Invariance (2015, methodology): “To show that and based on the analysis and the conclusions of this paper, we introduced and studied in (Elhoseiny et al., 2015) several variants of CNN architectures for joint learning of pose and category, which outperform the state of the art .”
MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving (2016, methodology): “In the context of deep learning, [7] proposed a model which is able to jointly perform pose estimation and object classification.”