.png){kind=icon}
返回
Improving loss function for deep convolutional neural network applied in automatic image annotation
.png){kind=icon}
PRE
AI
DOI：10.1007/s00371-023-02873-3.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Automatic image annotation (AIA) is a mechanism for describing the visual content of an image with a list of semantic labels. Typically, there is a massive imbalance between positive and negative tags in a picture-in other words, an image includes much fewer positive labels than negative ones. This imbalance can negatively affect the optimization process and diminish the emphasis on gradients from positive labels during training. Although traditional annotation models mainly focus on model structure design, we propose a novel unsymmetrical loss function for a deep convolutional neural network (CNN) that performs differently on positives and negatives, which leads to a reduction in the loss contribution from negative labels and also highlights the contribution of positive ones. During the annotation process, we specify a threshold for each label separately based on the Matthews correlation coefficient (MCC). Extensive experiments on high-vocabulary datasets like Corel 5k, IAPR TC-12, and Esp Game reveal that despite ignoring the semantic relationships between labels, our suggested approach achieves remarkable results compared to the state-of-the-art automatic image annotation models.
Keyword:
Image annotation
Deep learning
Unsymmetrical loss function
Threshold estimation
期刊
IF:
2.9
论文数:
4.6K
被引数:
6.5K
机构
引用论文
Learning semantic dependencies with channel correlation for multi-label classification.png)
VISUAL COMPUTER
VISUAL COMPUTERIF2.9
PREAI
分享收藏A novel and efficient xanthenic dye–organometallic ion‐pair complex for photoinitiating polymerization一种用于光引发聚合的新型高效的黄原胶染料-有机金属离子对配合物
PREAI
分享收藏分享收藏A Semi-supervised Learning Approach Based on Adaptive Weighted Fusion for Automatic Image Annotation基于自适应加权融合的半监督学习图像自动标注方法
PREAI
分享收藏Structural study of lanthanides(III) in aqueous nitrate and chloride solutions by EXAFS通过EXAFS对硝酸盐和氯化物水溶液中镧系元素 (III) 的结构研究
PREAI
分享收藏The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation在二元分类评估中，马修斯相关系数 (MCC) 相对于F1得分和准确性的优势BMC GENOMICS
OAAI
BMC GENOMICSIF3.7
OAAI分享收藏分享收藏
查看更多内容