Generalizing a Person Retrieval Model Hetero- and Homogeneously

By Zhun Zhong, Liang Zheng, Shaozi Li, Yi Yang. European Conference on Computer Vision, 2018

479 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/fc8b1413bbaf78d7b6fd2559342de8180c566d31

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yi Yang
2. Yunchao Wei
3. Hongsheng Li
4. Ling Shao
5. Thomas S. Huang
6. Tao A. Xiang
7. Liang Zheng
8. Tao Qin

In Computer Vision and Pattern Recognition

1. Yi Yang
2. Luc Van Gool
3. Dacheng Tao
4. Xiaogang Wang
5. Ling Shao
6. Liang Zheng
7. Ming-Hsuan Yang
8. Tao A. Xiang

Citations in the corpus

• Hierarchical Clustering With Hard-Batch Triplet Loss for Person Re-Identification (2019, background): “0 HHL[36] Transfer 62.”
• Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification (2020, methodology): “Zhong et al. (Zhong et al. 2018) translate images to different camera styles with CycleGAN (Zhu et al. 2017), and then use both real and generated images to reduce inter-camera variation.”
• Learning to Generate Novel Domains for Domain Generalization (2020, unknown): “We follow the recent unsupervised domain adaptation (UDA) methods in the person re-ID literature [58, 59, 32] and experiment with Market1501→Duke and Duke→Market1501.”
• Joint Discriminative and Generative Learning for Person Re-Identification (2019, methodology): “StarGAN [7] is used in [59] to generate pedestrian images with different camera styles.”
• Unsupervised Domain Adaptation Through Synthesis For Person Re-Identification (2020, methodology): “3 HHL [15] 62.”
• Distilled Person Re-Identification: Towards a More Scalable System (2019, methodology): “We compared with unsupervised ReID methods including unsupervised features LOMO [31], BOW [66] and unsupervised learning models UMDL [42], PTGAN [53], PUL [14], CAMEL [62], SPGAN [13], TJAIDL [51] and HHL [71].”
• Image-to-Image Translation: Methods and Applications (2021, methodology): “I2I methods can also contribute to other visual tasks, such as transfer learning for reinforcement learning [217], image registration [38], domain adaptation [29], [30], [31], person re-identification [218], [219], [220], [221], [222], image segmentation [7], [8], [9], facial geometry reconstruction”
• Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification (2020, background): “HHL (Zhong et al., 2018) learned camera-invariant features with camera style transferred images.”
• Adaptive Transfer Network for Cross-Domain Person Re-Identification (2019, background): “Recently, a few of UDA approaches tailored for person reidentification [2, 45, 46, 33, 3] have bee proposed upon the domain translation model CycleGAN [48].”
• Perceive Where to Focus: Learning Visibility-Aware Part-Level Features for Partial Person Re-Identification (2019, result): “the discriminative ability of the learned features, under both partial re-ID scenario (Partial-iLIDS) and holistic person re-ID scenario (Market-1501). This observation is consistent with prior works [9,38,30,29] on holistic person re-ID task. Second, comparing “MVPM-1” with “VPM”, we observe a dram”
• Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-Identification (2019, methodology): “Taking this into account, we enforce the camera-invariance [43] under the assumption that a person image and the corresponding camera-style transferred images should be close to each other.”
• Omni-Scale Feature Learning for Person Re-Identification (2019, unknown): “4 HHL [88] Market1501 + Duke (U ) 46.”
• Deep Learning for Person Re-Identification: A Survey and Outlook (2020, methodology): “These methods include PUL [208], CAMEL [206], PTGAN [118], TJ-AIDL [109], HHL [215], DAS [122], MAR [210], ENC [105], ATNet [216], PAUL [157], SBGAN [217], UCDA [219], CASC [211], PDA [119], CR-GAN [218], PAST [220], SSG [213].”
• Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID (2020, unknown): “P top-1 top-5 top-10 PUL [8] TOMM’18 20.5 45.5 60.7 66.7 16.4 30.0 43.4 48.5 TJ-AIDL [43] CVPR’18 26.5 58.2 74.8 81.1 23.0 44.3 59.6 65.0 SPGAN [6] CVPR’18 22.8 51.5 70.1 76.8 22.3 41.1 56.6 63.0 HHL [56] ECCV’18 31.4 62.2 78.8 84.0 27.2 46.9 61.0 66.7 ARN [22] CVPRW’18 39.4 70.3 80.4 86.3 33.4 60.2”
• Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification (2018, background): “In [49], Zhong et al. introduce a HeteroHomogeneous Learning (HHL) method, which aims to improve the generalization ability of re-ID models on the target set by achieving camera invariance and domain connectedness simultaneously.”
• Learning to Reduce Dual-Level Discrepancy for Infrared-Visible Person Re-Identification (2019, methodology): “In particular, we use ResNet-50 as the backbone network of F and follow the training strategy in [27].”
• Unsupervised Person Re-Identification via Multi-Label Classification (2020, methodology): “s, including unsupervised learning methods: LOMO [18], BOW [42], BUC [20] and DBC [4], and transfer learning based approaches: PUL [6], PTGAN [31], SPGAN [3], CAMEL [37], MMFA [19], TJ-AIDL [30], HHL [45], ECN [46], MAR [38], PAUL [36], SSG [7], CR-GAN [1], CASCL [32], PDA-Net [17], UCDA [24] and PA”
• Style Normalization and Restitution for Generalizable Person Re-Identification (2020, methodology): “UDAbased ReID methods can be roughly divided into three categories: style transfer [3, 44, 26], attribute recognition [43, 49, 33], and target-domain pseudo label estimation [5, 37, 58, 40, 52, 50].”
• Cluster Contrast for Unsupervised Person Re-Identification (2021, methodology): “The other is the unsupervised domain adaptation person re-ID, which first pre-trains a model on the source labeled dataset, and then fine-tunes the model on the target unlabeled dataset [12,29,48,51,59,67,68].”