Self Paced Deep Learning for Weakly Supervised Object Detection

24 May 2016Enver SanginetoMoin NabiDubravko CulibrkNicu Sebe

In a weakly-supervised scenario object detectors need to be trained using image-level annotation alone. Since bounding-box-level ground truth is not available, most of the solutions proposed so far are based on an iterative, Multiple Instance Learning framework in which the current classifier is used to select the highest-confidence boxes in each image, which are treated as pseudo-ground truth in the next training iteration... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Weakly Supervised Object Detection PASCAL VOC 2007 Self-Paced Learning MAP 38.11 # 25