What makes for effective detection proposals?
This work provides insights and metrics for selecting and tuning proposal methods in object detection, addressing a key bottleneck for researchers and practitioners in computer vision.
The paper analyzed twelve detection proposal methods and four baselines to understand their trade-offs in object detection, finding that improving proposal localization accuracy is as crucial as recall and introducing a novel metric, average recall (AR), which correlates well with detection performance.
Current top performing object detectors employ detection proposals to guide the search for objects, thereby avoiding exhaustive sliding window search across images. Despite the popularity and widespread use of detection proposals, it is unclear which trade-offs are made when using them during object detection. We provide an in-depth analysis of twelve proposal methods along with four baselines regarding proposal repeatability, ground truth annotation recall on PASCAL, ImageNet, and MS COCO, and their impact on DPM, R-CNN, and Fast R-CNN detection performance. Our analysis shows that for object detection improving proposal localisation accuracy is as important as improving recall. We introduce a novel metric, the average recall (AR), which rewards both high recall and good localisation and correlates surprisingly well with detection performance. Our findings show common strengths and weaknesses of existing methods, and provide insights and metrics for selecting and tuning proposal methods.