Abstract
In person re-identification (Re-ID), the data annotation cost of supervised learning, is huge and it cannot adapt well to complex situations. Therefore, compared with supervised deep learning methods, unsupervised methods are more in line with actual needs. In unsupervised learning, a key to solving Re-ID is to find a standard that can effectively distinguish the difference (distance) between the features of images belonging to different pedestrian identities. However, there are some differences in the images captured by different cameras (such as brightness, angle, etc.). It is well known that the training of neural networks is mainly based on the distance between features, while in unsupervised learning, especially in unsupervised learning methods based on hierarchical clustering, the distance between features plays a more important role in the clustering phase. We improve the accuracy of a deep learning method based on hierarchical clustering under fully unsupervised conditions, starting from both feature and distance metrics. First, we propose to use spherical features, by normalizing the images in the feature space, to weaken the structural differences (length) between features, while saving the feature differences (direction) between different identities. Then, we use the sum of squared errors (SSE) as a regularization term to balance different cluster states. We evaluate our method on four large-scale Re-ID datasets, and experiments show that our method achieves better results than the state-of-the-art unsupervised methods.
- [1] . 2020. Enforcing affinity feature learning through self-attention for person re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16, 1 (2020), 1–22.Google Scholar
Digital Library
- [2] . 2021. Unsupervised multi-source domain adaptation for person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 12914–12923.Google Scholar
Cross Ref
- [3] . 2018. Deep association learning for unsupervised video person re-identification. arXiv preprint arXiv:1808.07301 (2018).Google Scholar
- [4] . 2016. Person re-identification by multi-channel parts-basedCNN with improved triplet loss function. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1335–1344.Google Scholar
Cross Ref
- [5] . 2018. Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 994–1003.Google Scholar
Cross Ref
- [6] . 2019. Towards better validity: Dispersion based clustering for unsupervised person re-identification. arXiv preprint arXiv:1906.01308 (2019).Google Scholar
- [7] . 2015. Deep feature learning with relative distance comparison for person re-identification. Pattern Recognition 48, 10 (2015), 2993–3003.Google Scholar
Digital Library
- [8] . 2020. Adaptive exploration for unsupervised person re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16, 1 (2020), 1–19.Google Scholar
Digital Library
- [9] . 2018. Unsupervised person re-identification: Clustering and fine-tuning. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 14, 4 (2018), 83.Google Scholar
- [10] . 2019. SphereReID: Deep hypersphere manifold embedding for person re-identification. Journal of Visual Communication and Image Representation 60 (2019), 51–58.Google Scholar
Digital Library
- [11] . 2020. Delving deeper in drone-based person Re-Id by employing deep decision forest and attributes fusion. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16, 1s (2020), 1–15.Google Scholar
Digital Library
- [12] . 2014. DeepReID: Deep filter pairing neural network for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 152–159.Google Scholar
Digital Library
- [13] . 2020. Part-based structured representation learning for person re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16, 4 (2020), 1–22.Google Scholar
Digital Library
- [14] . 2020. Spatial preserved graph convolution networks for person re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16, 1s (2020), 1–14.Google Scholar
Digital Library
- [15] . 2019. A bottom-up clustering approach to unsupervised person re-identification. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 8738–8745.Google Scholar
Digital Library
- [16] . 2020. Unsupervised person re-identification via softened similarity learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3390–3399.Google Scholar
Cross Ref
- [17] . 2017. End-to-end comparative attention networks for person re-identification. IEEE Transactions on Image Processing 26, 7 (2017), 3492–3506.Google Scholar
Digital Library
- [18] . 2017. Sphereface: Deep hypersphere embedding for face recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 212–220.Google Scholar
Cross Ref
- [19] . 2020. Generalizing person re-identification by camera-aware invariance learning and cross-domain mixup. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XV 16. Springer, 224–241.Google Scholar
Digital Library
- [20] . 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9, Nov (2008), 2579–2605.Google Scholar
- [21] . 2019. Pose-guided feature alignment for occluded person re-identification. In Proceedings of the IEEE International Conference on Computer Vision. 542–551.Google Scholar
Cross Ref
- [22] . 2021. GreyReID: A novel two-stream deep framework with RGB-grey information for person re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 17, 1 (2021), 1–22.Google Scholar
Digital Library
- [23] . 2018. Pose-normalized image generation for person re-identification. In Proceedings of the European Conference on Computer Vision (ECCV). 650–667.Google Scholar
Cross Ref
- [24] . 2019. Auto-ReID: Searching for a part-aware ConvNet for person re-identification. In Proceedings of the IEEE International Conference on Computer Vision. 3750–3759.Google Scholar
Cross Ref
- [25] . 2016. Performance measures and a data set for multi-target, multi-camera tracking. In European Conference on Computer Vision Workshop on Benchmarking Multi-Target Tracking.Google Scholar
Cross Ref
- [26] . 2016. Performance measures and a data set for multi-target, multi-camera tracking. In European Conference on Computer Vision. Springer, 17–35.Google Scholar
Cross Ref
- [27] . 2020. Correlation discrepancy insight network for video re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16, 4 (2020), 1–21.Google Scholar
Digital Library
- [28] . 2016. Embedding deep metric for person re-identification: A study against large variations. In European Conference on Computer Vision. Springer, 732–748.Google Scholar
Cross Ref
- [29] . 2018. From deterministic to generative: Multimodal stochastic RNNs for video captioning. IEEE Transactions on Neural Networks and Learning Systems 30, 10 (2018), 3047–3058.Google Scholar
Cross Ref
- [30] . 2018. Self-supervised video hashing with hierarchical binary auto-encoder. IEEE Transactions on Image Processing 27, 7 (2018), 3210–3221.Google Scholar
Cross Ref
- [31] . 2017. Pose-driven deep convolutional model for person re-identification. In Proceedings of the IEEE International Conference on Computer Vision. 3960–3969.Google Scholar
Cross Ref
- [32] . 2019. Dissecting person re-identification from the viewpoint of viewpoint. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 608–617.Google Scholar
Cross Ref
- [33] . 2018. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). In Proceedings of the European Conference on Computer Vision (ECCV). 480–496.Google Scholar
Cross Ref
- [34] . 2018. Eliminating background-bias for robust person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5794–5803.Google Scholar
Cross Ref
- [35] . 2016. Gated siamese convolutional neural network architecture for human re-identification. In European Conference on Computer Vision. Springer, 791–808.Google Scholar
Cross Ref
- [36] . 2016. A siamese long short-term memory architecture for human re-identification. In European Conference on Computer Vision. Springer, 135–153.Google Scholar
Cross Ref
- [37] . 2020. Unsupervised person re-identification via multi-label classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10981–10990.Google Scholar
Digital Library
- [38] . 2018. Learning discriminative features with multiple granularities for person re-identification. In 2018 ACM Multimedia Conference on Multimedia Conference. ACM, 274–282.Google Scholar
Digital Library
- [39] . 2018. Equidistance constrained metric learning for person re-identification. Pattern Recognition 74 (2018), 38–51.Google Scholar
Digital Library
- [40] . 2018. Transferable joint attribute-identity deep learning for unsupervised person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2275–2284.Google Scholar
Cross Ref
- [41] . 2018. Person transfer GAN to bridge domain gap for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 79–88.Google Scholar
Cross Ref
- [42] . 2019. Progressive learning for person re-identification with one example. IEEE Transactions on Image Processing 28, 6 (2019), 2872–2881.Google Scholar
Cross Ref
- [43] . 2018. Exploit the unknown gradually: One-shot video-based person re-identification by stepwise learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5177–5186.Google Scholar
Cross Ref
- [44] . 2017. Joint detection and identification feature learning for person search. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3415–3424.Google Scholar
Cross Ref
- [45] . 2016. Unsupervised deep embedding for clustering analysis. In International Conference on Machine Learning. 478–487.Google Scholar
Digital Library
- [46] . 2003. Distance metric learning with application to clustering with side-information. In Advances in Neural Information Processing Systems. 521–528.Google Scholar
Digital Library
- [47] . 2019. Patch-based discriminative feature learning for unsupervised person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3633–3642.Google Scholar
Cross Ref
- [48] . 2018. Robust anchor embedding for unsupervised video person re-identification in the wild. In Proceedings of the European Conference on Computer Vision (ECCV). 170–186.Google Scholar
Cross Ref
- [49] . 2019. Dynamic graph co-matching for unsupervised video-based person re-identification. IEEE Transactions on Image Processing 28, 6 (2019), 2976–2990.Google Scholar
Cross Ref
- [50] . 2014. Deep metric learning for person re-identification. In 2014 22nd International Conference on Pattern Recognition. IEEE, 34–39.Google Scholar
Digital Library
- [51] . 2017. Cross-view asymmetric metric learning for unsupervised person re-identification. In Proceedings of the IEEE International Conference on Computer Vision. 994–1002.Google Scholar
Cross Ref
- [52] . 2019. Unsupervised person re-identification by soft multilabel learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2148–2157.Google Scholar
Cross Ref
- [53] . 2019. Robust person re-identification by modelling feature uncertainty. In Proceedings of the IEEE International Conference on Computer Vision. 552–561.Google Scholar
Cross Ref
- [54] . 2020. Hierarchical clustering with hard-batch triplet loss for person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 13657–13665.Google Scholar
Cross Ref
- [55] . 2021. Coarse-to-fine person re-identification with auxiliary-domain classification and second-order information bottleneck. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 598–607.Google Scholar
Cross Ref
- [56] . 2017. AlignedReID: Surpassing human-level performance in person re-identification. arXiv preprint arXiv:1711.08184.Google Scholar
- [57] . 2016. MARS: A video benchmark for large-scale person re-identification. In European Conference on Computer Vision. Springer, 868–884.Google Scholar
Cross Ref
- [58] . 2015. Scalable person re-identification: A benchmark. In Proceedings of the IEEE International Conference on Computer Vision. 1116–1124.Google Scholar
Digital Library
- [59] . 2017. Person re-identification in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1367–1376.Google Scholar
Cross Ref
- [60] . 2019. A siamese pedestrian alignment network for person re-identification. In Chinese Conference on Pattern Recognition and Computer Vision (PRCV). Springer, 409–420.Google Scholar
Digital Library
- [61] . 2019. Joint discriminative and generative learning for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2138–2147.Google Scholar
Cross Ref
- [62] . 2017. A discriminatively learned CNN embedding for person reidentification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 14, 1 (2017), 1–20.Google Scholar
Digital Library
- [63] . 2017. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In Proceedings of the IEEE International Conference on Computer Vision. 3754–3762.Google Scholar
Cross Ref
- [64] . 2018. Pedestrian alignment network for large-scale person re-identification. IEEE Transactions on Circuits and Systems for Video Technology.Google Scholar
- [65] . 2020. Random erasing data augmentation. In AAAI. 13001–13008.Google Scholar
- [66] . 2019. Invariance matters: Exemplar memory for domain adaptive person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 598–607.Google Scholar
Cross Ref
- [67] . 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
Index Terms
Clustering Matters: Sphere Feature for Fully Unsupervised Person Re-identification
Recommendations
Unsupervised Person Re-identification: Clustering and Fine-tuning
Special Section on Deep Learning for Intelligent Multimedia AnalyticsThe superiority of deeply learned pedestrian representations has been reported in very recent literature of person re-identification (re-ID). In this article, we consider the more pragmatic issue of learning a deep feature with no or only a few labels. ...
Unsupervised Person Re-Identification via Multi-Label Classification
AbstractThe challenge of unsupervised person re-identification (ReID) lies in learning discriminative features without true labels. Most of previous works predict single-class pseudo labels through clustering. To improve the quality of generated pseudo ...
Unsupervised Person Re-identification with Multi-Level Feature Contrastive Learning
CNIOT '23: Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of ThingsUnsupervised person re-identification works mainly rely on feature representation learning. In recent years, many methods have used pseudo-labels generated from clustering and applied contrast learning techniques to train models. However, the existing ...






Comments