Camera Contrast Learning for Unsupervised Person Re-Identification

Zhang, Guoqing; Wang, Lin; Chandran, Arun; Xuan, Jianhua

doi:10.1109/tcsvt.2023.3240001

Cited by 32 publications

(10 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We first list camera-agnostic methods, including BUC, 14 HCT, 13 SpCL, 6 HCD, 16 MPRD, 35 MaskPre, 36 CPLN, 37 RMCL, 38 and AdaMG 39 . The BUC 14 algorithm proposes a bottom-up clustering framework that exploits both the diversity across different identities and similarity within the same identity in the clustering procedure.…”

Section: Methodsmentioning

confidence: 99%

“…RMCL 38 designs a stability estimation scheme to improve pseudo label reliability modeling and introduces an identity hard contrastive loss to increase the robustness for hard samples. AdaMG 39 develops a multi-branch structure with adaptive memorization, in which a group of labels are generated for one sample and the corresponding memory dictionaries are updated adaptively according to the confidences of samples.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Joint global feature and part-based pyramid features for unsupervised person re-identification

Zhang,

Fan,

Zhou

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

In recent years, unsupervised person re-identification (re-ID) has attracted a lot of attention because it can save manual annotation costs and adapt to new scenes more conveniently in real-world applications. We focus on fully unsupervised learning-based re-ID, which aims to train a discriminative model based on unlabeled person images. In unsupervised learning, we need to generate pseudo labels by clustering convolutional features and then train convolutional neural network (CNN) models with these pseudo labels. The features used in the clustering process play an important role to ensure the quality of pseudo labels. Hence, we propose an enhancing feature extraction method to increase the reliability of generated pseudo labels and thus facilitate CNN model training. In order to enrich the obtained features, we carry out the feature extraction from both global and local aspects. The global features are extracted with ResNet50 backbone as many existing methods do. The local features are extracted by an additional part-based feature pyramid structure, in which the person image is divided into three parts and the features are extracted from each part with a pyramid structure. Then, we fuse the multi-layer pyramid features for each part as the local features. According to the joint global features and local features, the pseudo labels are predicted using clustering algorithms and further refined based on the similarity between global and local features. In addition, we design an inter-camera association learning component to effectively learn the ID discrimination ability across cameras. Extensive experiments on three large and representative person re-ID datasets demonstrate the effectiveness of the proposed approach.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Joint global feature and part-based pyramid features for unsupervised person re-identification

Zhang,

Fan,

Zhou

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…LP (Lan et al 2023) introduces a teacher-student network to reduce the interference of noisy labels during training. DCDP (Chen et al 2023) generates two sets of pseudo labels using two separate networks and introduces a consistent sample mining strategy. Besides, HNGN ) incorporates a ReID network and a hard negative generation network into a joint framework, training them alternately using an adversarial approach.…”

Section: Related Work Unsupervised Reidmentioning

confidence: 99%

Catalyst for Clustering-Based Unsupervised Object Re-identification: Feature Calibration

Li,

Hu,

2024

AAAI

View full text Add to dashboard Cite

Clustering-based methods are emerging as a ubiquitous technology in unsupervised object Re-Identification (ReID), which alternate between pseudo-label generation and representation learning. Recent advances in this field mainly fall into two groups: pseudo-label correction and robust representation learning. Differently, in this work, we improve unsupervised object ReID from feature calibration, a completely different but complementary insight from the current approaches. Specifically, we propose to insert a conceptually simple yet empirically powerful Feature Calibration Module (FCM) before pseudo-label generation. In practice, FCM calibrates the features using a nonparametric graph attention network, enforcing similar instances to move together in the feature space while allowing dissimilar instances to separate. As a result, we can generate more reliable pseudo-labels using the calibrated features and further improve subsequent representation learning. FCM is simple, effective, parameter-free, training-free, plug-and-play, and can be considered as a catalyst, increasing the ’chemical reaction’ between pseudo-label generation and representation learning. Moreover, it maintains the efficiency of testing time with negligible impact on training time. In this paper, we insert FCM into a simple baseline. Experiments across different scenarios and benchmarks show that FCM consistently improves the baseline (e.g., 8.2% mAP gain on MSMT17), and achieves the new state-of-the-art results. Code is available at: https://github.com/lhf12278/FCM-ReID.

show abstract

“…This performance gap can be attributed not only to the typical obstacles encountered in general object detection, including occlusions and lighting variations, but also to specific issues inherent to SOD. Specifically, existing feature extractors [3][4][5][6][7][8] have limitations in representing features for small objects, as conventional downsampling operations result in the deprivation of details associated with small objects, and small object features are susceptible to contamination from backgrounds and other instances, making it challenging for networks to capture the discriminative information required for subsequent tasks. Furthermore, the problem of sample imbalance between easy and difficult examples causes models to overlook the learning of regular samples and challenging ones during the optimization process, further affecting SOD performance.…”

Section: Introductionmentioning

confidence: 99%

FFEDet: Fine-Grained Feature Enhancement for Small Object Detection

Zhao,

Zhang,

Zhang

2024

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Small object detection poses significant challenges in the realm of general object detection, primarily due to complex backgrounds and other instances interfering with the expression of features. This research introduces an uncomplicated and efficient algorithm that addresses the limitations of small object detection. Firstly, we propose an efficient cross-scale feature fusion attention module called ECFA, which effectively utilizes attention mechanisms to emphasize relevant features across adjacent scales and suppress irrelevant noise, tackling issues of feature redundancy and insufficient representation of small objects. Secondly, we design a highly efficient convolutional module named SEConv, which reduces computational redundancy while providing a multi-scale receptive field to improve feature learning. Additionally, we develop a novel dynamic focus sample weighting function called DFSLoss, which allows the model to focus on learning from both normal and challenging samples, effectively addressing the problem of imbalanced difficulty levels among samples. Moreover, we introduce Wise-IoU to address the impact of poor-quality examples on model convergence. We extensively conduct experiments on four publicly available datasets to showcase the exceptional performance of our method in comparison to state-of-the-art object detectors.

show abstract

Camera Contrast Learning for Unsupervised Person Re-Identification

Cited by 32 publications

References 68 publications

Joint global feature and part-based pyramid features for unsupervised person re-identification

Joint global feature and part-based pyramid features for unsupervised person re-identification

Catalyst for Clustering-Based Unsupervised Object Re-identification: Feature Calibration

FFEDet: Fine-Grained Feature Enhancement for Small Object Detection

Contact Info

Product

Resources

About