Focal Loss for Dense Object Detection

ICCV 2017 Tsung-Yi LinPriya GoyalRoss GirshickKaiming HePiotr Dollár

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a regular, dense sampling of possible object locations have the potential to be faster and simpler, but have trailed the accuracy of two-stage detectors thus far... (read more)

PDF Abstract

Code


Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Object Detection COCO test-dev RetinaNet (ResNeXt-101-FPN) box AP 40.8 # 41
Object Detection COCO test-dev RetinaNet (ResNeXt-101-FPN) AP50 61.1 # 35
Object Detection COCO test-dev RetinaNet (ResNeXt-101-FPN) AP75 44.1 # 37
Object Detection COCO test-dev RetinaNet (ResNeXt-101-FPN) APS 24.1 # 30
Object Detection COCO test-dev RetinaNet (ResNeXt-101-FPN) APM 44.2 # 29
Object Detection COCO test-dev RetinaNet (ResNeXt-101-FPN) APL 51.2 # 41
Object Detection COCO test-dev RetinaNet (ResNet-101-FPN) box AP 39.1 # 51
Object Detection COCO test-dev RetinaNet (ResNet-101-FPN) AP50 59.1 # 44
Object Detection COCO test-dev RetinaNet (ResNet-101-FPN) AP75 42.3 # 45
Object Detection COCO test-dev RetinaNet (ResNet-101-FPN) APS 21.8 # 44
Object Detection COCO test-dev RetinaNet (ResNet-101-FPN) APM 42.7 # 35
Object Detection COCO test-dev RetinaNet (ResNet-101-FPN) APL 50.2 # 44