Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification

Suncheng Xiang

Shanghai Jiao Tong University

The FineGPR dataset is generated by a popular GTA5 game engine that can synthesise images under controllable viewpoints, weathers,illuminations and backgrounds, as well as 13 fine-grained attributes at the identity level.

Our FineGPR dataset provides fine-grained and accurately configurable annotations, including 36 different viewpoints, 7 different kinds of weathers, 7 different kinds of illuminations, and 9 different kinds of backgrounds.

Definition of different viewpoints. Viewpoints of one identity are sampled at an interval of 10°, e.g. 0°-80° denotes that a person has 9 different angles in total.

The exemplars of different weather distribution (left) and illumination distribution (right) from the proposed FineGPR dataset.

The distributions of attributes at the identity level on FineGPR. The left figure shows the numbers of IDs for each attribute. The middle and right pies illustrate the distribution of the colors of upper-body and low-body clothes respectively.

Some visual exemplars with ID-level pedestrian attributes in the proposed FineGPR dataset, such as Wear short sleeve , Wear dress, Wear hat, Carry bag, etc.

Comparison with existing datasets
Link of the Dataset
Method
Results
Extendibility
Citation

Comparison with existing datasets

Some Mainstream Datasets for Person Re-Identification

For FineGPR (for details of the pervious related work, please refer to the GPR Homepage) :

dataset	IDs	boxs	cams	weathers	illumination	scene	resolution
Market-1501	1,501	32,668	6	-	-	-	low
CUHK03	1,467	14,096	2	-	-	-	low
DukeMTMC-reID	1,404	36,411	8	-	-	-	low
MSMT17	4,101	126,441	15	-	-	-	vary
--------------	---------	------	------	----------	--------------	--------------	--------------
SOMAset	50	100,000	250	-	-	-	-
SyRI	100	1,680,000	100	-	140	-	-
PersonX	1,266	273,456	36	-	-	6	vary
Unreal	3,000	120,000	34	-	-	1	low
RandPerson	8,000	1,801,816	19	-	6	11	low
FineGPR	1150	2,028,600	36	7	7	9	high

Link of the Dataset

Data of FineGPR for Viewpoint Analysis

A small subset of FineGPR can be downloaded from the following links:

SJTU Yun Drive:
- Download Link password: qbdg
Baidu Yun Drive:
- Download Link password: wp3p

Directories & Files of images

FineGPR_v1
├── 0001/ # this number is coresponds with the IDs of different images.
│   ├── 0001_c01_w01_l01_p01.jpg  
│   ├── 0001_c01_w01_l02_p01.jpg
│   ├── 0001_c01_w01_l03_p01.jpg	   
│   └── ...
├── 0002/
│   ├── 0002_c01_w01_l01_p01.jpg  
│   ├── 0002_c01_w01_l02_p01.jpg
│   ├── 0002_c01_w01_l03_p01.jpg	   
│   └── ...
├── ...
└── readme.txt

Name of the image

Taking "0001_c01_w01_l01_p01.jpg" as an example:

0001 is the id of the person
c01 is the id of the camera
w01 is the id of the weather
l01 is the id of the illumination
p01 is the id of the background

Viewpoint annotations

FineGPR
├── c01：90°      ├── c10：180°      ├── c19：270°      ├── c28：0°
├── c02：100°     ├── c11：190°      ├── c20：280°      ├── c29：10°
├── c03：110°     ├── c12：200°      ├── c21：290°      ├── c30：20°
├── c04：120°     ├── c13：210°      ├── c22：300°      ├── c31：30°
├── c05：130°     ├── c14：220°      ├── c23：310°      ├── c32：40°
├── c06：140°     ├── c15：230°      ├── c24：320°      ├── c33：50°
├── c07：150°     ├── c16：240°      ├── c25：330°      ├── c34：60°
├── c08：160°     ├── c17：250°      ├── c26：340°      ├── c35：70°
└── c09：170°     └── c18：260°      └── c27：350°      └── c36：80°

Weather annotations

FineGPR
├── w01：Sunny
├── w02：Clouds    
├── w03：Overcast
├── w04：Foggy   
├── w05：Neutral
├── w06：Blizzard 
└── w07：Snowlight

Illumination annotations

FineGPR
├── l01：Midnight
├── l02：Dawn    
├── l03：Forenoon
├── l04：Noon   
├── l05：Afternoon
├── l06：Dusk 
└── l07：Night

Scene annotations

FineGPR
├── p01：Urban
├── p02：Urban   
├── p03：Wild
├── p04：Urban   
├── p05：Wild
├── p06：Urban
├── p07：Urban
├── p08：Wild 
└── p09：Urban

Method

The two-stage pipeline AOST to learn attribute distribution of target domain. Firstly, we learn attribute distribution of real domain on the basis of XGBoost & PSO learning system. Secondly, we perform style transfer to enhance the reality of optimal dataset. Finally, the transferred data are adopted for downstream re-ID task.

Results

Performance comparison with existing Real and Synthetic datasets on Market-1501, DukeMTMC-reID and CUHK03, respectively. Our re-ID baseline system is built only with commonly used softmax cross-entropy loss on vanilla ResNet-50 with no bells and whistles

References

[1] Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. CVPR 2018.
[2] Bag of tricks and a strong baseline for deep person re-identification. CVPRW 2019.

Extendibility

Accompanied with our FineGPR, we also provide some human body masks (Middle) and keypoint locations (Bottom) of all characters during the annotation. We hope that our synthetic dataset FineGPR can not only contribute a lot to the development of generalizable person re-ID, but also advance the research of other computer vision tasks, such as human part segmentation and pose estimation.

Citation

If you use our FineGPR dataset for your research, please cite our paper.

@article{xiang2021less,
  title={Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification},
  author={Xiang, Suncheng and You, Guanjie and Guan, Mengyuan and Chen, Hao and Wang, Feng and Liu, Ting and Fu, Yuzhuo},
  journal={arXiv preprint arXiv:2109.10498},
  year={2021}
}

For further questions and suggestions about our datasets and methods, please feel free to contact Suncheng Xiang: xiangsuncheng17@sjtu.edu.cn

821736960/FineGPR