资源论文Adaptively Unified Semi-supervised Learning for Cross-Modal Retrieval

Adaptively Unified Semi-supervised Learning for Cross-Modal Retrieval

2019-11-05 | |  76 |   53 |   0

Abstract Motivated by the fact that both relevancy of class labels and unlabeled data can help to strengthen multi-modal correlation, this paper proposes a novel method for cross-modal retrieval. To make each sample moving to the direction of its relevant label while far away from that of its irrelevant ones, a novel dragging technique is fused into a unifified linear regression model. By this way, not only the relation between embedded features and relevant class labels but also the relation between embedded features and irrelevant class labels can be exploited. Moreover, considering that some unlabeled data contain specifific semantic information, a weighted regression model is designed to adaptively enlarge their contribution while weaken that of the unlabeled data with non-specifific semantic information. Hence, unlabeled data can supply semantic information to enhance discriminant ability of classififier. Finally, we integrate the constraints into a joint minimization formulation and develop an effifi- cient optimization algorithm to learn a discriminative common subspace for different modalities. Experimental results on Wiki, Pascal and NUS-WIDE datasets show that the proposed method outperforms the state-of-the-art methods even when we set 20% samples without class labels

上一篇:Adaptive Semi-supervised Learning with Discriminative Least Squares Regression

下一篇:Learning deep structured network for weakly supervised change detection

用户评价
全部评价

热门资源

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • Rating-Boosted La...

    The performance of a recommendation system reli...

  • Hierarchical Task...

    We extend hierarchical task network planning wi...