No Spare Parts: Sharing Part Detectors for Image Categorization
This addresses the problem of efficient and effective image categorization for computer vision applications, offering an incremental advance in part-based modeling.
The paper tackles image categorization by proposing that distinctive parts should be shared across categories rather than selected separately, and it achieves competitive results with state-of-the-art methods, including improvements over deep convolutional neural networks.
This work aims for image categorization using a representation of distinctive parts. Different from existing part-based work, we argue that parts are naturally shared between image categories and should be modeled as such. We motivate our approach with a quantitative and qualitative analysis by backtracking where selected parts come from. Our analysis shows that in addition to the category parts defining the class, the parts coming from the background context and parts from other image categories improve categorization performance. Part selection should not be done separately for each category, but instead be shared and optimized over all categories. To incorporate part sharing between categories, we present an algorithm based on AdaBoost to jointly optimize part sharing and selection, as well as fusion with the global image representation. We achieve results competitive to the state-of-the-art on object, scene, and action categories, further improving over deep convolutional neural networks.