본문 바로가기

쓰기

 
발표자 김누리 
발표일자 2022-10-05 
저자 Wang, Xudong, et al. 
학회명 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022. 
논문지  
This work studies the bias issue of pseudo-labeling, a natural phenomenon that widely occurs but often overlooked by prior research. Pseudo-labels are generated when a classifier trained on source data is transferred to unlabeled target data. We observe heavy long-tailed pseudo-labels when a semi-supervised learning model FixMatch predicts labels on the unlabeled set even though the unlabeled data is curated to be balanced. Without intervention, the training model inherits the bias from the pseudo-labels and end up being sub-optimal. To eliminate the model bias, we propose a simple yet effective method DebiasMatch, comprising of an adaptive debiasing module and an adaptive marginal loss. The strength of debiasing and the size of margins can be automatically adjusted by making use of an online updated queue. Benchmarked on ImageNet-1K, DebiasMatch significantly outperforms previous state-of-the-arts by more than 26% and 10.5% on semi-supervised learning (0.2% annotated data) and zero-shot learning tasks respectively.

    2022

      Template-free Prompt Tuning for Few-shot NER
      2022.12.15
      발표자: 안지민     발표일자: 2022-12-15     저자: Ruotian Ma1, Xin Zhou1, Tao Gui2, Yiding Tan1, Linyang Li1, Qi Zhang1, Xuanjing Huang1     학회명: NAACL 2021    
      Towards Unsupervised Domain Generalization
      2022.10.12
      발표자: 이진섭     발표일자: 2022-10-12     저자: Haiyang Yang* , Linjun Zhou*, Renzhe Xu, Peng Cui†, Zheyan Shen, Haoxin Liu     학회명: 2022 CVPR