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.
Introduction
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 |
Notes
- 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 codebase. - Most of models are trained for
8Xschedule on BigDetection. - Most of pretrained models are finetuned for
1Xschedule on COCO. TTAdenotes test time augmentation.- Pre-trained models of Swin Transformer can be downloaded from Swin Transformer for ImageNet Classification.
Getting Started
Requirements
Ubuntu 16.04CUDA 10.2
Installation
# 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 https://download.openmmlab.com/mmcv/dist/cu102/torch1.8.0/index.html
# Clone and install
git clone https://github.com/amazon-research/bigdetection.git
cd bigdetection
pip install -r requirements/build.txt
pip install -v -e .
# Install Apex (optinal)
git clone https://github.com/NVIDIA/apex
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/data
└── 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
Training
To train a detector with pre-trained models, run:
# multi-gpu training
tools/dist_train.sh <CONFIG_FILE> <GPU_NUM> --cfg-options load_from=<PRETRAIN_MODEL>
Pre-training
To pre-train a CBNetV2 with a Swin-Base backbone on BigDetection using 8 GPUs, run: (PRETRAIN_MODEL should be pre-trained checkpoint of Base-Swin-Transformer: model)
tools/dist_train.sh configs/BigDetection/cbnetv2/htc_cbv2_swin_base_giou_4conv1f_adamw_bigdet.py 8 \
--cfg-options load_from=<PRETRAIN_MODEL>
To pre-train a Deformable-DETR with a ResNet-50 backbone on BigDetection, run:
tools/dist_train.sh configs/BigDetection/deformable_detr/deformable_detr_r50_16x2_8x_bigdet.py 8
Fine-tuning
To fine-tune a BigDetection pre-trained CBNetV2 (with Swin-Base backbone) on COCO, run: (PRETRAIN_MODEL should be BigDetection pre-trained checkpoint of CBNetV2: model)
tools/dist_train.sh configs/BigDetection/cbnetv2/htc_cbv2_swin_base_giou_4conv1f_adamw_20e_coco.py 8 \
--cfg-options load_from=<PRETRAIN_MODEL>
Inference
To evaluate a detector with pre-trained checkpoints, run:
tools/dist_test.sh <CONFIG_FILE> <CHECKPOINT> <GPU_NUM> --eval bbox
BigDetection evaluation
To evaluate pre-trained CBNetV2 on BigDetection validation, run:
tools/dist_test.sh configs/BigDetection/cbnetv2/htc_cbv2_swin_base_giou_4conv1f_adamw_bigdet.py \
<BIGDET_PRETRAIN_CHECKPOINT> 8 --eval bbox
COCO evaluation
To evaluate COCO-finetuned CBNetV2 on COCO validation, run:
# without test-time-augmentation
tools/dist_test.sh configs/BigDetection/cbnetv2/htc_cbv2_swin_base_giou_4conv1f_adamw_20e_coco.py \
<COCO_FINETUNE_CHECKPOINT> 8 --eval bbox mask
# with test-time-augmentation
tools/dist_test.sh configs/BigDetection/cbnetv2/htc_cbv2_swin_base_giou_4conv1f_adamw_20e_coco_tta.py \
<COCO_FINETUNE_CHECKPOINT> 8 --eval bbox mask
Other configuration based on Detectron2 can be found at detectron2-probject.
Citation
If you use our dataset or pretrained models in your research, please kindly consider to cite the following paper.
@article{bigdetection2022,
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},
year={2022}
}
Security
See CONTRIBUTING for more information.
License
This project is licensed under the Apache-2.0 License.
Acknowledgement
We thank the authors releasing mmdetection and CBNetv2 for object detection research community.
191 Dec 31, 2022
48 Dec 30, 2022
209 Dec 29, 2022
137 Dec 15, 2022
7.6k Jan 1, 2023
43 Dec 26, 2022
3 Jul 7, 2022
26 Nov 4, 2022
284 Dec 21, 2022
37 Dec 8, 2022
126 Dec 3, 2022
86 Dec 7, 2022
92 Sep 28, 2021
1 Jan 5, 2022
2 Jan 11, 2022
3 Aug 20, 2022
432 Dec 16, 2022
33 Jun 27, 2021
36 Oct 30, 2022