Locating Objects Without Bounding Boxes

CVPR 2019 β€’ Javier Ribera β€’ David GΓΌera β€’ Yuhao Chen β€’ Edward J. Delp

Recent advances in convolutional neural networks (CNN) have achieved remarkable results in locating objects in images. In these networks, the training procedure usually requires providing bounding boxes or the maximum number of expected objects... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Object Localization Mall Hausdorff Loss Precision 88.1 # 1
Object Localization Plant Hausdorff Loss F-Score 88.6 # 1
Object Localization Pupil Hausdorff Loss Recall 89.2 # 1

Methods used in the Paper


METHOD TYPE
πŸ€– No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet