How important are Deformable Parts in the Deformable Parts Model?
This work questions a foundational assumption in computer vision object detection, potentially shifting focus to component-based methods, though it is incremental in refining an existing model.
The study challenges the belief that deformable parts are the main contributor to the Deformable Parts Model's performance, showing that increasing components and using appearance-based clustering yields significant improvements, and that part deformations can be disabled with minimal performance loss.
The main stated contribution of the Deformable Parts Model (DPM) detector of Felzenszwalb et al. (over the Histogram-of-Oriented-Gradients approach of Dalal and Triggs) is the use of deformable parts. A secondary contribution is the latent discriminative learning. Tertiary is the use of multiple components. A common belief in the vision community (including ours, before this study) is that their ordering of contributions reflects the performance of detector in practice. However, what we have experimentally found is that the ordering of importance might actually be the reverse. First, we show that by increasing the number of components, and switching the initialization step from their aspect-ratio, left-right flipping heuristics to appearance-based clustering, considerable improvement in performance is obtained. But more intriguingly, we show that with these new components, the part deformations can now be completely switched off, yet obtaining results that are almost on par with the original DPM detector. Finally, we also show initial results for using multiple components on a different problem -- scene classification, suggesting that this idea might have wider applications in addition to object detection.