.png){kind=icon}
返回
Probabilistic embeddings revisited
.png){kind=icon}
PRE
AI
DOI：10.1007/s00371-023-03087-3.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In recent years, deep metric learning and its probabilistic extensions claimed state-of-the-art results in the face verification task. Despite improvements in face verification, probabilistic methods received little attention in the research community and practical applications. Previous metric learning benchmarks avoided comparison with probabilistic methods, and it is still unclear whether they generalize well to image retrieval tasks beyond faces. In this paper, we, for the first time, perform an in-depth analysis and unified comparison of known probabilistic methods in verification and retrieval tasks. We study different design choices and argue that many of them have limited impact, while only a few probabilistic methods surpass modern metric learning approaches. Combining the best ideas of earlier works, we propose a simple modification of the top-performing method, achieving new state-of-the-art results among probabilistic methods. Finally, we study confidence prediction and show that it correlates with data quality, but contains little information about prediction error probability. We thus provide a new confidence evaluation benchmark and establish a baseline for future confidence prediction research. PyTorch implementation is publicly released.
Keyword:
Probabilistic metric learning
Metric learning
Computer vision
Image retrieval
期刊
IF:
2.9
论文数:
4.6K
被引数:
6.5K
机构
暂无机构信息
引用论文
.png){kind=icon}
分享收藏Structural and functional alterations in the androgen receptor in spinal bulbar muscular atrophy
PREAI
分享收藏
查看更多内容