.png){kind=icon}
返回
Learning Multiple Criteria Calibration for Generalized Zero-shot Learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2024.112131.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Generalized Zero-shot Learning (GZSL) seeks to identify objects from both seen and unseen classes, relying solely on labeled samples from the seen classes. One of GZSL's main challenges is the problem of bias towards seen classes, i.e., , the model tends to classify all test samples as seen classes due to the data imbalance and over-fitting. To reduce the prediction bias, we proposed to train a novel M ultiple C riteria C alibration (MCC) model with C onfusion eliMination M ination contrastive E mbedding (CME). Specifically, we designed a novel divide- and-conquer calibration network by leveraging the learned multiple Class-Level and Instance-Level criteria to separate unseen samples from seen samples. To enhance feature separation, we further formulated supervised confusion-elimination contrastive constraints in the latent space to ensure the alignment properties of visual- semantic features and simultaneously encourage the learned features to distribute uniformly, providing a reasonable distribution for MCC and classification. After that, to adaptively mitigate bias, we can follow the learned criteria to calibrate the predictions of both the seen and unseen classes in the latent space, or leave the original predictions unchanged. Extensive experiments under GZSL settings show that the proposed method outperforms the state-of-the-art methods on four popular benchmarks.
Keyword:
Generalized Zero-shot Learning
Contrastive learning
Calibration model
Multiple criteria calibration
期刊
K
IF:
7.6
论文数:
1.2W
被引数:
4.5W
机构
引用论文
.png){kind=icon}
Distribution and gradient constrained embedding model for zero-shot learning with fewer seen samples
OAAI
OAAI分享收藏
查看更多内容