mmdetection/configs/objects365

Objects365 Dataset

Objects365 Dataset

Abstract

Objects365 Dataset V1

Objects365 Dataset V1 is a brand new dataset, designed to spur object detection research with a focus on diverse objects in the Wild. It has 365 object categories over 600K training images. More than 10 million, high-quality bounding boxes are manually labeled through a three-step, carefully designed annotation pipeline. It is the largest object detection dataset (with full annotation) so far and establishes a more challenging benchmark for the community. Objects365 can serve as a better feature learning dataset for localization-sensitive tasks like object detection and semantic segmentation.

Objects365 Dataset V2

Objects365 Dataset V2 is based on the V1 release of the Objects365 dataset. Objects 365 annotated 365 object classes on more than 1800k images, with more than 29 million bounding boxes in the training set, surpassing PASCAL VOC, ImageNet, and COCO datasets. Objects 365 includes 11 categories of people, clothing, living room, bathroom, kitchen, office/medical, electrical appliances, transportation, food, animals, sports/musical instruments, and each category has dozens of subcategories.

Citation

@inproceedings{shao2019objects365,
  title={Objects365: A large-scale, high-quality dataset for object detection},
  author={Shao, Shuai and Li, Zeming and Zhang, Tianyuan and Peng, Chao and Yu, Gang and Zhang, Xiangyu and Li, Jing and Sun, Jian},
  booktitle={Proceedings of the IEEE/CVF international conference on computer vision},
  pages={8430--8439},
  year={2019}
}

Prepare Dataset

1. You need to download and extract Objects365 dataset. Users can download Objects365 V2 by using tools/misc/download_dataset.py.

Usage

   python tools/misc/download_dataset.py --dataset-name objects365v2 \
   --save-dir ${SAVING PATH} \
   --unzip \
   --delete  # Optional, delete the download zip file

Note: There is no download link for Objects365 V1 right now. If you would like to download Objects365-V1, please visit official website to concat the author.

1. The directory should be like this:

   mmdetection
   ├── mmdet
   ├── tools
   ├── configs
   ├── data
   │   ├── Objects365
   │   │   ├── Obj365_v1
   │   │   │   ├── annotations
   │   │   │   │   ├── objects365_train.json
   │   │   │   │   ├── objects365_val.json
   │   │   │   ├── train        # training images
   │   │   │   ├── val          # validation images
   │   │   ├── Obj365_v2
   │   │   │   ├── annotations
   │   │   │   │   ├── zhiyuan_objv2_train.json
   │   │   │   │   ├── zhiyuan_objv2_val.json
   │   │   │   ├── train        # training images
   │   │   │   │   ├── patch0
   │   │   │   │   ├── patch1
   │   │   │   │   ├── ...
   │   │   │   ├── val          # validation images
   │   │   │   │   ├── patch0
   │   │   │   │   ├── patch1
   │   │   │   │   ├── ...

Results and Models

Objects365 V1

Architecture	Backbone	Style	Lr schd	Mem (GB)	box AP	Config	Download
Faster R-CNN	R-50	pytorch	1x	-	19.6	config	model | log
Faster R-CNN	R-50	pytorch	1350K	-	22.3	config	model | log
Retinanet	R-50	pytorch	1x	-	14.8	config	model | log
Retinanet	R-50	pytorch	1350K	-	18.0	config	model | log

Objects365 V2

Architecture	Backbone	Style	Lr schd	Mem (GB)	box AP	Config	Download
Faster R-CNN	R-50	pytorch	1x	-	19.8	config	model | log
Retinanet	R-50	pytorch	1x	-	16.7	config	model | log