The Role of Context Selection in Object Detection
This work addresses a specific problem in computer vision for object detection researchers, offering an incremental improvement by refining context modeling.
The authors tackled the limited utility of context in object detection by proposing a region-based context re-scoring method with dynamic selection to reduce noise and enhance informative context, achieving significant improvement in mean average precision (mAP) on the SUN RGB-D dataset compared to baseline detectors.
We investigate the reasons why context in object detection has limited utility by isolating and evaluating the predictive power of different context cues under ideal conditions in which context provided by an oracle. Based on this study, we propose a region-based context re-scoring method with dynamic context selection to remove noise and emphasize informative context. We introduce latent indicator variables to select (or ignore) potential contextual regions, and learn the selection strategy with latent-SVM. We conduct experiments to evaluate the performance of the proposed context selection method on the SUN RGB-D dataset. The method achieves a significant improvement in terms of mean average precision (mAP), compared with both appearance based detectors and a conventional context model without the selection scheme.