paper-with-me

홈 › Papers

Enhancing Representations through Heterogeneous Self-Supervised Learning

2023-10-08 · Zhong-Yu Li, Bo-Wen Yin, Yongxiang Liu, Li Liu, Ming-Ming Cheng

Incorporating heterogeneous representations from different architectures has facilitated various vision tasks, e.g., some hybrid networks combine transformers and convolutions. However, complementarity between such heterogeneous architectures has not been well exploited in self-supervised learning. Thus, we propose Heterogeneous Self-Supervised Learning (HSSL), which enforces a base model to learn from an auxiliary head whose architecture is heterogeneous from the base model. In this process, HSSL endows the base model with new characteristics in a representation learning way without structural changes. To comprehensively understand the HSSL, we conduct experiments on various heterogeneous pairs containing a base model and an auxiliary head. We discover that the representation quality of the base model moves up as their architecture discrepancy grows. This observation motivates us to propose a search strategy that quickly determines the most suitable auxiliary head for a specific base model to learn and several simple but effective methods to enlarge the model discrepancy. The HSSL is compatible with various self-supervised methods, achieving superior performances on various downstream tasks, including image classification, semantic segmentation, instance segmentation, and object detection. Our source code will be made publicly available.

📄 PDF Abstract BibTeX arXiv:2310.05108

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage ClassificationInstance Segmentationobject-detectionObject DetectionRepresentation LearningSelf-Supervised LearningSemantic Segmentation

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Cross-view Self-Supervised Learning on Heterogeneous Graph Neural Network via Bootstrapping

2022-01-10 · Minjae Park

Heterogeneous graph neural networks can represent information of heterogeneous graphs with excellent ability. Recently, self-supervised learning manner is researched which learns the unique expression of a graph through …

Contrastive LearningGraph Neural NetworkSelf-Supervised Learning

Enhancing 2D Representation Learning with a 3D Prior

2024-06-04 · Mehmet Aygün, Prithviraj Dhar, Zhicheng Yan, Oisin Mac Aodha 외

Learning robust and effective representations of visual data is a fundamental task in computer vision. Traditionally, this is achieved by training models with labeled data which can be expensive to obtain. Self-supervise…

Representation LearningSelf-Supervised Learning

Graph Masked Autoencoder for Spatio-Temporal Graph Learning

2024-10-14 · Qianru Zhang, Haixin Wang, Siu-Ming Yiu, Hongzhi Yin

Effective spatio-temporal prediction frameworks play a crucial role in urban sensing applications, including traffic analysis, human mobility behavior modeling, and citywide crime prediction. However, the presence of dat…

Crime PredictionData AugmentationGraph LearningSelf-Supervised Learning

HGOT: Self-supervised Heterogeneous Graph Neural Network with Optimal Transport

2025-06-03 · Yanbei Liu, Chongxu Wang, Zhitao Xiao, Lei Geng 외

Heterogeneous Graph Neural Networks (HGNNs), have demonstrated excellent capabilities in processing heterogeneous information networks. Self-supervised learning on heterogeneous graphs, especially contrastive self-superv…

Graph Neural NetworkNode ClassificationSelf-Supervised Learning

Learning Genomic Sequence Representations using Graph Neural Networks over De Bruijn Graphs

2023-12-06 · Kacper Kapuśniak, Manuel Burger, Gunnar Rätsch, Amir Joudaki

The rapid expansion of genomic sequence data calls for new methods to achieve robust sequence representations. Existing techniques often neglect intricate structural details, emphasizing mainly contextual information. To…

Contrastive LearningRetrieval