Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework-Reference-Cited by-同舟云学术

Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework

Published:2022-06 Issue: Volume: Page:
ISSN:
Container-title:2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Zhang Shu¹,Xu Ran¹,Xiong Caiming¹,Ramaiah Chetan¹

Affiliation:

1. Salesforce Research

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9878378/9878366/09880213.pdf?arnumber=9880213

Reference49 articles.

1. Ranked List Loss for Deep Metric Learning

2. Infor-mation theoretic measures for clusterings comparison: Vari-ants, properties, normalization and correction for chance;vinh;The Journal of Machine Learning Research,2010

3. Contrastive multiview coding;tian;ArXiv Preprint,2019

4. Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases

5. Improved deep metric learning with multi-class n-pair loss objective;sohn;Advances in neural information processing systems,0

Cited by 25 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Deconfounded hierarchical multi-granularity classification;Computer Vision and Image Understanding;2024-11

2. Fake review detection with label-consistent and hierarchical-relation-aware graph contrastive learning;Knowledge-Based Systems;2024-10

3. TL-CCL: Two-level causal contrastive learning for multi-label ocular disease diagnosis with fundus images;Biomedical Signal Processing and Control;2024-09

4. TagRec++: Hierarchical Label Aware Attention Network for Question Categorization;IEEE Transactions on Knowledge and Data Engineering;2024-07

5. Location-aware Fashion Attribute Recognition and Retrieval;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30