.png){kind=icon}
返回
Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations
.png){kind=icon}
OA
AI
DOI：10.1109/TMM.2021.3115335.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Unsupervised pretraining is of great significance for visual representation. Especially, contrastive learning has achieved great success recently, but existing approaches mostly ignored spatial information which is often crucial for visual representation. Strong semantic embedding has an inherent advantage for classification, but dense prediction tasks require more spatial and low-level representation. This paper presents heterogeneous contrastive learning (HCL), an effective approach that adds spatial information to the encoding stage to alleviate the learning inconsistency between the contrastive objective and strong data augmentation operations. We demonstrate the effectiveness of HCL by showing that (i) it achieves higher accuracy in instance discrimination, (ii) it surpasses existing pre-training methods in a series of downstream tasks (iii) and it shrinks the pre-training costs by half for almost 800 GPU-hours. More importantly, we show that our approach achieves higher efficiency in visual representations, and thus delivers a key message to inspire the future research of self-supervised visual representation learning.
Keyword:
Feature extraction
Semantics
Head
Contrastive learning
pre-training
spatial information
期刊
IF:
9.7
论文数:
4.5K
被引数:
2.4W
机构
引用论文
SIFT: predicting amino acid changes that affect protein functionSIFT: 预测影响蛋白质功能的氨基酸变化.png)
NUCLEIC ACIDS RESEARCH
OAAI
NUCLEIC ACIDS RESEARCHIF13.1
OAAI分享收藏分享收藏分享收藏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Indoor AirOAAI
Indoor AirIF0
OAAI分享收藏
查看更多内容