Inverting and Visualizing Features for Object Detection
Abstract
This paper presents methods to visualize feature spaces commonly used in object detection. The tools in this paper allow a human to put on "feature space glasses" and see the visual world as a computer might see it. We found that these "glasses" allow us to gain insight into the behavior of computer vision systems. We show a variety of experiments with our visualizations, such as examining the linear separability of recognition in HOG space, generating high scoring "super objects" for an object detector, and diagnosing false positives. We pose the visualization problem as one of feature inversion, i.e. recovering the natural image that generated a feature descriptor. We describe four algorithms to tackle this task, with different trade-offs in speed accuracy, and scalability. Our most successful algorithm uses ideas from sparse coding to learn a pair of dictionaries that enable regression between HOG features and natural images, and can invert features at interactive rates. We believe these visualizations are useful tools to add to an object detector researcher's toolbox, and code is available.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 23, 2012
- Accession Number
- ADA569642
Entities
People
- Aditya Khosla
- Antonio Torralba
- Carl Vondrick
- Tomasz Malisiewicz
Organizations
- Massachusetts Institute of Technology