Abstract
Person re-identification (ReID) plays an important role in applications such as public security and video surveillance. Recently, learning from synthetic data [9], which benefits from the popularity of the synthetic data engine, has attracted great attention from the public. However, existing datasets are limited in quantity, diversity, and realisticity, and cannot be efficiently used for the ReID problem. To address this challenge, we manually construct a large-scale person dataset named FineGPR with fine-grained attribute annotations. Moreover, aiming to fully exploit the potential of FineGPR and promote the efficient training from millions of synthetic data, we propose an attribute analysis pipeline called AOST based on the traditional machine learning algorithm, which dynamically learns attribute distribution in a real domain, then eliminates the gap between synthetic and real-world data and thus is freely deployed to new scenarios. Experiments conducted on benchmarks demonstrate that FineGPR with AOST outperforms (or is on par with) existing real and synthetic datasets, which suggests its feasibility for the ReID task and proves the proverbial less-is-more principle. Our synthetic FineGPR dataset is publicly available at https://github.com/JeremyXSC/FineGPR.
- [1] . 2018. Domain adaptation through synthesis for unsupervised person re-identification. In Proceedings of the European Conference on Computer Vision. 189–205.Google Scholar
- [2] . 2018. Looking beyond appearances: Synthetic training data for deep CNNs in re-identification. Computer Vision and Image Understanding 167 (2018), 50–62.Google Scholar
Digital Library
- [3] . 2018. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Proceedings of the Conference on Fairness, Accountability, and Transparency. 77–91.Google Scholar
- [4] . 2016. XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 785–794.Google Scholar
Digital Library
- [5] . 2019. Learning semantic segmentation from synthetic data: A geometrically guided input-output adaptation approach. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1841–1850.Google Scholar
Cross Ref
- [6] . 2014. Consistent re-identification in a camera network. In Proceedings of the European Conference on Computer Vision. 330–345.Google Scholar
Cross Ref
- [7] . 2009. ImageNet: A large-scale hierarchical image database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
IEEE ,Los Alamitos, CA , 248–255.Google ScholarCross Ref
- [8] . 2018. Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 994–1003.Google Scholar
Cross Ref
- [9] . 2021. MOTSynth: How can synthetic data help pedestrian detection and tracking? In Proceedings of the IEEE/CVF International Conference on Computer Vision. 10849–10859.Google Scholar
Cross Ref
- [10] . 2016. Image style transfer using convolutional neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2414–2423.Google Scholar
Cross Ref
- [11] . 2017. The EU General Data Protection Regulation (GDPR): European regulation that has a global impact. International Journal of Market Research 59, 6 (2017), 703–705.Google Scholar
Cross Ref
- [12] . 2014. Generative adversarial nets. In Advances in Neural Information Processing Systems 27.Google Scholar
Digital Library
- [13] . 2007. Evaluating appearance models for recognition, reacquisition, and tracking. In Proceedings of the IEEE International Workshop on Performance Evaluation for Tracking and Surveillance, Vol. 3. 1–7.Google Scholar
- [14] . 2016. Deep residual learning for image recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 770–778.Google Scholar
Cross Ref
- [15] . 2017. In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017).Google Scholar
- [16] . 2017. GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In Advances in Neural Information Processing Systems 30.Google Scholar
- [17] . 1995. Particle swarm optimization. In Proceedings of the International Conference on Neural Networks (ICNN’95), Vol. 4.
IEEE ,Los Alamitos, CA , 1942–1948.Google ScholarCross Ref
- [18] . 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- [19] . 2014. DeepReid: Deep filter pairing neural network for person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 152–159.Google Scholar
Digital Library
- [20] . 2020. Spatial preserved graph convolution networks for person re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications 16, 1s (2020), 1–14.Google Scholar
Digital Library
- [21] . 2015. Person re-identification by local maximal occurrence representation and metric learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2197–2206.Google Scholar
Cross Ref
- [22] . 2014. Microsoft COCO: Common objects in context. In Proceedings of the European Conference on Computer Vision. 740–755.Google Scholar
Cross Ref
- [23] . 2020. Unity style transfer for person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 6887–6896.Google Scholar
Cross Ref
- [24] . 2019. Bag of tricks and a strong baseline for deep person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.Google Scholar
Cross Ref
- [25] . 2018. Two at once: Enhancing learning and generalization capacities via IBN-Net. In Proceedings of the European Conference on Computer Vision. 464–479.Google Scholar
Digital Library
- [26] . 2012. Teaching 3D geometry to deformable part models. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
IEEE ,Los Alamitos, CA , 3362–3369.Google ScholarCross Ref
- [27] . 2016. Performance measures and a data set for multi-target, multi-camera tracking. In Proceedings of the European Conference on Computer Vision. 17–35.Google Scholar
Cross Ref
- [28] . 2018. Learning to simulate. arXiv preprint arXiv:1810.02513 (2018).Google Scholar
- [29] . 2009. Learning discriminative appearance-based models using partial least squares. In Proceedings of the XXII Brazilian Symposium on Computer Graphics and Image Processing.
IEEE ,Los Alamitos, CA , 322–329.Google ScholarDigital Library
- [30] . 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).Google Scholar
- [31] . 2019. Dissecting person re-identification from the viewpoint of viewpoint. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 608–617.Google Scholar
Cross Ref
- [32] . 2011. Unbiased look at dataset bias. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
IEEE ,Los Alamitos, CA , 1521–1528.Google ScholarDigital Library
- [33] . 2016. A Siamese long short-term memory architecture for human re-identification. In Proceedings of the European Conference on Computer Vision. 135–153.Google Scholar
Cross Ref
- [34] . 2019. Learning from synthetic data for crowd counting in the wild. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8198–8207.Google Scholar
Cross Ref
- [35] . 2020. Surpassing real-world source training data: Random 3D characters for generalizable person re-identification. In Proceedings of the 28th ACM International Conference on Multimedia. 3422–3430.Google Scholar
Digital Library
- [36] . 2018. Person transfer GAN to bridge domain gap for person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 79–88.Google Scholar
Cross Ref
- [37] . 2022. Learning from self-discrepancy via multiple co-teaching for cross-domain person re-identification. Machine Learning. Published online, June 14, 2022.Google Scholar
- [38] . 2020. Unsupervised domain adaptation through synthesis for person re-identification. In Proceedings of the IEEE International Conference on Multimedia and Expo.
IEEE ,Los Alamitos, CA , 1–6.Google ScholarCross Ref
- [39] . 2021. Taking a closer look at synthesis: Fine-grained attribute analysis for person re-identification. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing.
IEEE ,Los Alamitos, CA , 3765–3769.Google ScholarCross Ref
- [40] . 2021. Rethinking person re-identification via semantic-based pretraining. arXiv preprint arXiv:2110.05074 (2021).Google Scholar
- [41] . 2022. Rethinking illumination for person re-identification: A unified view. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4731–4739.Google Scholar
Cross Ref
- [42] . 2017. Joint detection and identification feature learning for person search. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3415–3424.Google Scholar
Cross Ref
- [43] . 2020. Simulating content consistent vehicle datasets with attribute descent. In Proceedings of the European Conference on Computer Vision. 775–791.Google Scholar
Digital Library
- [44] . 2021. UnrealPerson: An adaptive pipeline towards costless person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11506–11515.Google Scholar
Cross Ref
- [45] . 2018. Generalized cross entropy loss for training deep neural networks with noisy labels. In Proceedings of the 32nd International Conference on Neural Information Processing Systems.Google Scholar
Digital Library
- [46] . 2014. Learning mid-level filters for person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 144–151.Google Scholar
Digital Library
- [47] . 2022. JoT-GAN: A framework for jointly training GAN and person re-identification model. ACM Transactions on Multimedia Computing, Communications, and Applications 18, 1s (2022), 1–18.Google Scholar
Digital Library
- [48] . 2015. Scalable person re-identification: A benchmark. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 1116–1124.Google Scholar
Cross Ref
- [49] . 2017. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 3754–3762.Google Scholar
Cross Ref
- [50] . 2017. Re-ranking person re-identification with k-reciprocal encoding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1318–1327.Google Scholar
Cross Ref
- [51] . 2018. CamStyle: A novel data augmentation method for person re-identification. IEEE Transactions on Image Processing 28, 3 (2018), 1176–1190.Google Scholar
Digital Library
- [52] . 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 2223–2232.Google Scholar
Cross Ref
Index Terms
Less Is More: Learning from Synthetic Data with Fine-Grained Attributes for Person Re-Identification
Recommendations
Fine-Grained Person Re-identification
AbstractPerson re-identification (re-id) plays a critical role in tracking people via surveillance systems by matching people across non-overlapping camera views at different locations. Although most re-id methods largely depend on the appearance features ...
WePerson: Learning a Generalized Re-identification Model from All-weather Virtual Data
MM '21: Proceedings of the 29th ACM International Conference on MultimediaThe aim of person re-identification (Re-ID) is retrieving a person of interest across multiple non-overlapping cameras. Re-ID has gained significantly increased advancement in recent years. However, real data annotation is costly and model ...
Cross-dataset person re-identification using deep convolutional neural networks: effects of context and domain adaptation
Over the past years, the impact of surveillance systems on public safety increases dramatically. One significant challenge in this domain is person re-identification, which aims to detect whether a person has already been captured by another camera in ...






Comments