.png){kind=icon}
返回
Cross-modal de-deviation for enhancing few-shot classification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2024.110475.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Few -shot learning poses a critical challenge due to the deviation problem caused by the scarcity of available samples. In this work, we aim to address deviations in both feature representations and prototypes. To achieve this, we propose a cross -modal de -deviation framework that leverages class semantic information to provide robust prior knowledge for the samples. This framework begins with a visual -to -semantic autoencoder trained on the labeled samples to predict semantic features for the unlabeled samples. Then, we devise a binary linear programming model to match the initial prototypes with the cluster centers of the unlabeled samples. To circumvent potential mismatches between the cluster centers and the initial prototypes, we perform the label assignment process in the semantic space by transforming the cluster centers into semantic representations and utilizing the class ground truth semantic features as reference points. Moreover, we model a linear classifier with the concatenation of the refined prototypes and the class ground truth semantic features serving as the initial weights. Then we propose a novel optimization strategy based on the alternating least squares (ALS) model. From the ALS model, we can derive two closed -form solutions regarding to the features and weights, facilitating alternative optimization of them. Extensive experiments conducted on few -shot learning benchmarks demonstrate the competitive advantages of our CMDD method over the state-of-the-art approaches, confirming its effectiveness in reducing deviation. The code is available at: https://github.com/pmhDL/CMDD. git.
Keyword:
Cross-modal label assignment
Alternating least squares
Alternative optimization
Closed-form solution
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Fragment properties from large-scale asteroid collisions: I: Results from SPH/N-body simulations using porous parent bodies and improved material models.png)
Icarus
OAAI
IcarusIF0
OAAI分享收藏Relation fusion propagation network for transductive few-shot learning用于直推式少镜头学习的关系融合传播网络PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容