Learning Semantic Part-Based Models from Google Images
This work addresses the challenge of automating part-based model learning for computer vision, reducing reliance on manual annotations, but it is incremental as it builds on existing methods like R-CNN.
The paper tackles the problem of training semantic part-based models for object classes without manual part location annotations, using Google Images, and achieves a performance increase from 12.9 to 27.2 AP on the PASCAL-Part dataset.
We propose a technique to train semantic part-based models of object classes from Google Images. Our models encompass the appearance of parts and their spatial arrangement on the object, specific to each viewpoint. We learn these rich models by collecting training instances for both parts and objects, and automatically connecting the two levels. Our framework works incrementally, by learning from easy examples first, and then gradually adapting to harder ones. A key benefit of this approach is that it requires no manual part location annotations. We evaluate our models on the challenging PASCAL-Part dataset [1] and show how their performance increases at every step of the learning, with the final models more than doubling the performance of directly training from images retrieved by querying for part names (from 12.9 to 27.2 AP). Moreover, we show that our part models can help object detection performance by enriching the R-CNN detector with parts.