Attribute based object identification

Over the last years, the robotics community has made substantial progress in detection and 3D pose estimation of known and unknown objects. However, the question of how to identify objects based on language descriptions has not been investigated in detail. While the computer vision community recently started to investigate the use of attributes for object recognition, these approaches do not consider the task settings typically observed in robotics, where a combination of appearance attributes and object names might be used in referral language to identify specific objects in a scene. In this paper, we introduce an approach for identifying objects based on natural language containing appearance and name attributes. To learn rich RGB-D features needed for attribute classification, we extend recently introduced sparse coding techniques so as to automatically learn attribute-dependent features. We introduce a large data set of attribute descriptions of objects in the RGB-D object dataset. Experiments on this data set demonstrate the strong performance of our approach to language based object identification. We also show that our attribute-dependent features provide significantly better generalization to previously unseen attribute values, thereby enabling more rapid learning of new attribute values.

Authors

• Yuyin Sun
• Liefeng Bo
• Dieter Fox

Keywords

• Image color analysis
• Object recognition
• Shape
• Robots
• Materials
• Sun
• Training
• Object Identification
• Natural Language
• Rich Features
• Objects In The Scene
• Object Naming
• Sparse Coding
• Attribute Values
• Human Pose Estimation
• Unknown Objects
• Robotics Community
• Sparse Techniques
• Progress In Detection
• Raw Data
• Material Properties
• Unsupervised Learning
• Codebook
• Feature Learning
• Multinomial Regression
• Layer-by-layer
• Codeword
• Group Lasso
• Unsupervised Feature Learning
• Orthogonal Matching Pursuit
• Target Object
• Spatial Pooling
• Scene Dataset
• Object Instances
• Limited Training Samples