Robust Label Rectifying With Consistent Contrastive-Learning for Domain Adaptive Person Re-Identification

Song, Xulin

doi:10.1109/tmm.2021.3096014

Cited by 19 publications

(3 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multi-view learning has grown in popularity as a result of this concept. Meanwhile, contrastive learning has received intensive research in recent years showing that contrasting congruent and incongruent views of objects can help the algorithms learn expressive representations [28][29][30][31][32]. Inspired by these ideas, two different views are established for a graph and applied to learn discriminative node representations for classification.…”

Section: Feature Extractionmentioning

confidence: 99%

Individuality-enhanced and multi-granularity consistency-preserving graph neural network for semi-supervised node classification

Liu,

2023

Appl Intell

View full text Add to dashboard Cite

Semi-supervised node classification is an important task that aims at classifying nodes based on the graph structure, node features, and class labels for a subset of nodes. While most graph convolutional networks (GCNs) perform well when an ample number of labeled nodes are available, they often degenerate when the amount of labeled data is limited. To address this problem, we propose a scheme, namely, Individuality-enhanced and Multi-granularity Consistency-preserving graph neural Network (IMCN), which can alleviate the problem of losing individual information within the encoder while providing a reliable supervised signal for learning purposes. First, one simple encoder based on node features only is integrated to enhance node individuality and amend node commonality learned by the GCN-based encoder. Then, three constraints are defined at different levels of granularity, encompassing node embedding agreement, semantic class alignment, and node-to-class distribution identity. They can maintain the consistency between the individuality and commonality of nodes and be leveraged as latent supervised signals for learning representative embeddings. Finally, the trade-off between the individuality and commonality of nodes captured by two encoders is taken into consideration for node classification. Extensive experiments on six real-world datasets have been conducted to validate the superiority of IMCN against state-of-the-art baselines in handling node classification tasks with scarce labeled data. Graphical abstract

show abstract

Section: Feature Extractionmentioning

confidence: 99%

Individuality-enhanced and multi-granularity consistency-preserving graph neural network for semi-supervised node classification

Liu,

2023

Appl Intell

View full text Add to dashboard Cite

show abstract

“…The contrastive loss has become an excellent tool in unsupervised representation learning. It aims to maximize the similarities of positive pairs and minimize that of negative pairs [19], [20], [25]- [27]. The contrastive loss function is widely used for many kinds of data, such as images, text, audio, graphs, etc.…”

Section: A Contrastive Loss (Cl)mentioning

confidence: 99%

Multi-Sample based Contrastive Loss for Top-k Recommendation

Tang¹,

Zhao²,

Wu³

et al. 2021

Preprint

View full text Add to dashboard Cite

The top-k recommendation is a fundamental task in recommendation systems which is generally learned by comparing positive and negative pairs. The Contrastive Loss (CL) is the key in contrastive learning that has received more attention recently and we find it is well suited for top-k recommendations. However, it is a problem that CL treats the importance of the positive and negative samples as the same. On the one hand, CL faces the imbalance problem of one positive sample and many negative samples. On the other hand, positive items are so few in sparser datasets that their importance should be emphasized. Moreover, the other important issue is that the sparse positive items are still not sufficiently utilized in recommendations. So we propose a new data augmentation method by using multiple positive items (or samples) simultaneously with the CL loss function. Therefore, we propose a Multi-Sample based Contrastive Loss (MSCL) function which solves the two problems by balancing the importance of positive and negative samples and data augmentation. And based on the graph convolution network (GCN) method, experimental results demonstrate the state-of-the-art performance of MSCL. The proposed MSCL is simple and can be applied in many methods. We will release our code on GitHub upon the acceptance.

show abstract

“…Contrastive Learning. Contrastive learning is one of the most compelling methods in both unsupervised and supervised visual representation learning domains [41]- [43], which has been widely used in object detection [44]- [46], segmentation [47], [48], medical image [49], deraining [50], person reidentification [51], [52], personalized recommendation [53], [54], image captioning [55], [56], and natural language understanding [57]. Inspired by contrastive learning, the work of [58] focused on the inconsistency between audio and visual modalities, and use a contrastive loss to model inter-modality similarity for DeepFake video detection.…”

Section: Introductionmentioning

confidence: 99%

Multi-View Contrastive Learning with Virtual Social Group Influence for Social Recommendation

Zhang,

Li,

Zhang

2023

Preprint

View full text Add to dashboard Cite

Robust Label Rectifying With Consistent Contrastive-Learning for Domain Adaptive Person Re-Identification

Cited by 19 publications

References 49 publications

Individuality-enhanced and multi-granularity consistency-preserving graph neural network for semi-supervised node classification

Individuality-enhanced and multi-granularity consistency-preserving graph neural network for semi-supervised node classification

Multi-Sample based Contrastive Loss for Top-k Recommendation

Multi-View Contrastive Learning with Virtual Social Group Influence for Social Recommendation

Contact Info

Product

Resources

About