.png){kind=icon}
返回
Self-Supervised Learning by Estimating Twin Class Distribution
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2023.3266169.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We present Twist, a simple and theoretically explainable self-supervised representation learning method by classifying large-scale unlabeled datasets in an end-to-end way. We employ a siamese network terminated by a softmax operation to produce twin class distributions of two augmented images. Without supervision, we enforce the class distributions of different augmentations to be consistent. However, simply minimizing the divergence between augmentations will generate collapsed solutions, i.e., outputting the same class distribution for all images. In this case, little information about the input images is preserved. To solve this problem, we propose to maximize the mutual information between the input image and the output class predictions. Specifically, we minimize the entropy of the distribution for each sample to make the class prediction assertive, and maximize the entropy of the mean distribution to make the predictions of different samples diverse. In this way, Twist can naturally avoid the collapsed solutions without specific designs such as asymmetric network, stop-gradient operation, or momentum encoder. As a result, Twist outperforms previous state-of-the-art methods on a wide range of tasks. Specifically on the semi-supervised classification task, Twist achieves 61.2% top-1 accuracy with 1% ImageNet labels using a ResNet-50 as backbone, surpassing previous best results by an improvement of 6.2%. Codes and pre-trained models are available at https://github.com/bytedance/TWIST
Keyword:
Task analysis
Mutual information
Entropy
Probability distribution
Self-supervised learning
Classification algorithms
Neural networks
Unsupervised learning
image classification
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
分享收藏
分享收藏Thermal comfort, perceived air quality, and cognitive performance when personally controlled air movement is used by tropically acclimatized persons当热带适应的人使用个人控制的空气运动时，热舒适性，感知的空气质量和认知表现.png)
Indoor Air
OAAI
Indoor AirIF0
OAAI分享收藏分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏Role of simple descriptors and applicability domain in predicting change in protein thermostabilityPLOS ONEOAAI
PLOS ONEIF0
OAAI分享收藏
查看更多内容