Focal Loss for Dense Object Detection

Task	Dataset	Model	Metric name	Metric value	Global rank
Object Detection	COCO test-dev	RetinaNet (ResNeXt-101-FPN)	box AP	40.8	# 32
Object Detection	COCO test-dev	RetinaNet (ResNeXt-101-FPN)	AP50	61.1	# 32
Object Detection	COCO test-dev	RetinaNet (ResNeXt-101-FPN)	AP75	44.1	# 33
Object Detection	COCO test-dev	RetinaNet (ResNeXt-101-FPN)	APS	24.1	# 28
Object Detection	COCO test-dev	RetinaNet (ResNeXt-101-FPN)	APM	44.2	# 26
Object Detection	COCO test-dev	RetinaNet (ResNeXt-101-FPN)	APL	51.2	# 38
Object Detection	COCO test-dev	RetinaNet (ResNet-101-FPN)	box AP	39.1	# 42
Object Detection	COCO test-dev	RetinaNet (ResNet-101-FPN)	AP50	59.1	# 41
Object Detection	COCO test-dev	RetinaNet (ResNet-101-FPN)	AP75	42.3	# 41
Object Detection	COCO test-dev	RetinaNet (ResNet-101-FPN)	APS	21.8	# 42
Object Detection	COCO test-dev	RetinaNet (ResNet-101-FPN)	APM	42.7	# 32
Object Detection	COCO test-dev	RetinaNet (ResNet-101-FPN)	APL	50.2	# 41

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/focal-loss-for-dense-object-detection/object-detection-on-coco)](https://paperswithcode.com/sota/object-detection-on-coco?p=focal-loss-for-dense-object-detection)`

ICCV 2017 • Tsung-Yi Lin • Priya Goyal • Ross Girshick • Kaiming He • Piotr 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

Add Remove

tensorflow/models

58,507

facebookresearch/detectron

22,162

AlexeyAB/darknet

5,269

fizyr/keras-retinanet

3,219

pierluigiferrari/ssd_keras

1,355

See all 116 implementations

Tasks

Add Remove

DENSE OBJECT DETECTION

OBJECT DETECTION

Evaluation results from the paper

Add Remove

#32 best model for Object Detection on COCO test-dev

Get a GitHub badge

Task	Dataset	Model	Metric name	Metric value	Global rank	Compare
Object Detection	COCO test-dev	RetinaNet (ResNeXt-101-FPN)	box AP	40.8	# 32	See all
Object Detection	COCO test-dev	RetinaNet (ResNeXt-101-FPN)	AP50	61.1	# 32	See all
Object Detection	COCO test-dev	RetinaNet (ResNeXt-101-FPN)	AP75	44.1	# 33	See all
Object Detection	COCO test-dev	RetinaNet (ResNeXt-101-FPN)	APS	24.1	# 28	See all
Object Detection	COCO test-dev	RetinaNet (ResNeXt-101-FPN)	APM	44.2	# 26	See all
Object Detection	COCO test-dev	RetinaNet (ResNeXt-101-FPN)	APL	51.2	# 38	See all
Object Detection	COCO test-dev	RetinaNet (ResNet-101-FPN)	box AP	39.1	# 42	See all
Object Detection	COCO test-dev	RetinaNet (ResNet-101-FPN)	AP50	59.1	# 41	See all
Object Detection	COCO test-dev	RetinaNet (ResNet-101-FPN)	AP75	42.3	# 41	See all
Object Detection	COCO test-dev	RetinaNet (ResNet-101-FPN)	APS	21.8	# 42	See all
Object Detection	COCO test-dev	RetinaNet (ResNet-101-FPN)	APM	42.7	# 32	See all
Object Detection	COCO test-dev	RetinaNet (ResNet-101-FPN)	APL	50.2	# 41	See all

Focal Loss for Dense Object Detection

Code Edit Add Remove

Tasks Edit Add Remove

Evaluation results from the paper Edit Add Remove

Code

Add Remove

Tasks

Add Remove

Evaluation results from the paper

Add Remove