02 | BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learning 论文作者:Hongwei Zheng(Meituan),Linyuan Zhou(Meituan), Han Li(SJTU), Jinming Su(Meituan), Xiaoming Wei(Meituan),Xiaoming Xu(Meituan) 备注:SJTU(Shanghai Jiao Tong University) 论文地址:PDF 论文简介:长尾半监督...
《ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting》:这篇论文提出了一种用于场景文本检测和识别的文本图像进一步对齐的预训练方法。 《BEM: Balanced and Entropy based Mix for Long-Tailed Semi-Supervised Learning》:该论文提出了一种基于平衡和熵的混合方法,用...
Title: Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias Abstract:域适应是机器学习中的一个重要任务,旨在通过利用相关源域的知识来提高模型在目标域上的性能。在本工作中,我们引入了通用半监督域适应(Universal Semi-Supervised Domain Adaptation, UniSSDA),这是一种实用但具挑战性的设置...
Lee, Hyuck, and Heeyoung Kim. "CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024.
Density-guided Semi-supervised 3D Semantic Segmentation with Dual-space Hardness Sampling 论文作者:李嘉楠,董秋雷 现有的3D半监督语义分割通常使用点对点的对比学习,但这种技术容易受到外点影响,为解决该问题,我们提出了DDSemi。其中,DDSemi使用密度引导的点对锚的对...
赛题3:“EPIC-KITCHENS VISOR Semi-supervised VOS”挑战任务为半监督视频目标分割,要求跟踪和分割从第一帧注释中指定的目标对象。赛题数据集为官方发布的EPIC-KITCHENS VISOR数据集,该数据集已经成为在以第一人称的视频中分割手和活动对象...
Projects Security Insights Additional navigation options main 1Branch0Tags Code README Apache-2.0 license Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentation Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentation...
标题:BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learning 作者:Hongwei Zheng, Linyuan Zhou, Han Li (SJTU), Jinming Su, Xiaoming Wei, Xiaoming Xu (美团) 摘要:长尾半监督学习(LTSSL)因其数据分布不平衡和标注数据稀缺而极具挑战性。传统的数据混合方法无法解决类不平衡问题,且忽...
Infer from What You Have Seen Before: Temporally-dependent Classifier for Semi-supervised Video Segmentation Jiafan Zhuang, Zilei Wang, Yixin Zhang, Zhun Fan; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 3575-3584 ...
CVPR 2024: AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation - xmed-lab/AllSpark