Multi-View Priors for Learning Detectors from Sparse Viewpoint Data
This addresses the need for richer object detection models in computer vision, particularly for applications like autonomous driving, but it is incremental as it builds on existing transfer learning methods.
The paper tackles the problem of learning object detectors with rich outputs like viewpoint and 3D geometry from sparse training data by using transfer learning with multi-view priors, resulting in largely improved performance in 2D localization and viewpoint estimation on a challenging street scene dataset.
While the majority of today's object class models provide only 2D bounding boxes, far richer output hypotheses are desirable including viewpoint, fine-grained category, and 3D geometry estimate. However, models trained to provide richer output require larger amounts of training data, preferably well covering the relevant aspects such as viewpoint and fine-grained categories. In this paper, we address this issue from the perspective of transfer learning, and design an object class model that explicitly leverages correlations between visual features. Specifically, our model represents prior distributions over permissible multi-view detectors in a parametric way -- the priors are learned once from training data of a source object class, and can later be used to facilitate the learning of a detector for a target class. As we show in our experiments, this transfer is not only beneficial for detectors based on basic-level category representations, but also enables the robust learning of detectors that represent classes at finer levels of granularity, where training data is typically even scarcer and more unbalanced. As a result, we report largely improved performance in simultaneous 2D object localization and viewpoint estimation on a recent dataset of challenging street scenes.