BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training

By Likun Cai, Zhi Zhang, Yi Zhu, Li Zhang, Mu Li, Xiangyang Xue.

This repo is the official implementation of BigDetection. It is based on mmdetection and CBNetV2.


We construct a new large-scale benchmark termed BigDetection. Our goal is to simply leverage the training data from existing datasets (LVIS, OpenImages and Object365) with carefully designed principles, and curate a larger dataset for improved detector pre-training. BigDetection dataset has 600 object categories and contains 3.4M training images with 36M object bounding boxes. We show some important statistics of BigDetection in the following figure.

Left: Number of images per category of BigDetection. Right: Number of instances in different object sizes.

Results and Models

BigDetection Validation

We show the evaluation results on BigDetection Validation. We hope BigDetection could serve as a new challenging benchmark for evaluating next-level object detection methods.

Method mAP (bigdet val) Links
YOLOv3 9.7 model/config
Deformable DETR 13.1 model/config
Faster R-CNN (C4)* 18.9 model
Faster R-CNN (FPN)* 19.4 model
CenterNet2* 23.1 model
Cascade R-CNN* 24.1 model
CBNetV2-Swin-Base 35.1 model/config

COCO Validation

We show the finetuning performance on COCO minival/test-dev. Results show that BigDetection pre-training provides significant benefits for different detector architectures. We achieve 59.8 mAP on COCO test-dev with a single model.

Method mAP (coco minival/test-dev) Links
YOLOv3 30.5/- config
Deformable DETR 39.9/- model/config
Faster R-CNN (C4)* 38.8/- model
Faster R-CNN (FPN)* 40.5/- model
CenterNet2* 45.3/- model
Cascade R-CNN* 45.1/- model
CBNetV2-Swin-Base 59.1/59.5 model/config
CBNetV2-Swin-Base (TTA) 59.5/59.8 config

Data Efficiency

We followed STAC and SoftTeacher to evaluate on COCO for different partial annotation settings.

Method mAP (1%) mAP (2%) mAP (5%) mAP (10%)
Baseline 9.8 14.3 21.2 26.2
STAC 14.0 18.3 24.4 28.6
SoftTeacher (ICCV 21) 20.5 26.5 30.7 34.0
Ours 25.3 28.1 31.9 34.1
model model model model


  • The models following * are implemented on another detection codebase Detectron2. Here we provide the pretrained checkpoints. The results can be reproduced following the installation of CenterNet2 or Detectron2.
  • Most of models are trained for 8X schedule on BigDetection.
  • Most of pretrained models are finetuned for 1X schedule on COCO.
  • TTA denotes test time augmentation.
  • Pre-trained models of Swin Transformer can be downloaded from Swin Transformer for ImageNet Classification.

Getting Started


  • Ubuntu 16.04
  • CUDA 10.2


# Create conda environment
conda create -n bigdet python=3.7 -y
conda activate bigdet

# Install Pytorch
conda install pytorch==1.8.0 torchvision==0.9.0 cudatoolkit=10.2 -c pytorch

# Install mmcv
pip install mmcv-full==1.3.9 -f

# Clone and install
git clone
cd bigdetection
pip install -r requirements/build.txt
pip install -v -e .

# Install Apex (optinal)
git clone
cd apex
pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./

Data Preparation

Our BigDetection involves 3 datasets and train/val data can be downloaded from their official website (Objects365, OpenImages v6, LVIS v1.0). All datasets should be placed under $bigdetection/data/ as below. The synsets (total 600 class names) of BigDetection dataset can be downloaded here: bigdetection_synsets. Contact us with [email protected] to get access to our pre-processed annotation files.

└── BigDetection
    ├── annotations
    │   ├── bigdet_obj_train.json
    │   ├── bigdet_oid_train.json
    │   ├── bigdet_lvis_train.json
    │   ├── bigdet_val.json
    │   └── cas_weights.json
    ├── train
    │   ├── Objects365
    │   ├── OpenImages
    │   └── LVIS
    └── val


# single-gpu testing
python tools/ <CONFIG_FILE> <DET_CHECKPOINT_FILE> --eval bbox 

# multi-gpu testing


To train a detector with pre-trained models, run:

# multi-gpu training
tools/ <CONFIG_FILE> <GPU_NUM> --cfg-options load_from=<PRETRAIN_MODEL>


If you use our dataset or pretrained models in your research, please kindly consider to cite the following paper.

  title={BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training},
  author={Likun Cai and Zhi Zhang and Yi Zhu and Li Zhang and Mu Li and Xiangyang Xue},
  journal={arXiv preprint arXiv:2203.13249},


See CONTRIBUTING for more information.


This project is licensed under the Apache-2.0 License.


We thank the authors releasing mmdetection and CBNetv2 for object detection research community.


View Github