Content of Methodology and System of Machine Learning in our journal

        Published in last 1 year |  In last 2 years |  In last 3 years |  All
    Please wait a minute...
    For Selected: Toggle Thumbnails
    Enriching image descriptions by fusing fine-grained semantic features with a transformer
    WANG Junhao, LUO Yifeng
    Journal of East China Normal University(Natural Science)    2020, 2020 (5): 56-67.   DOI: 10.3969/j.issn.1000-5641.202091004
    Abstract （441）   HTML （38）    PDF （754KB）（156）      
    Modern image captioning models following the encoder-decoder architecture of a convolutional neural network (CNN) or recurrent neural network (RNN) face the issue of dismissing a large amount of detailed information contained in images and the high cost of training time. In this paper, we propose a novel model, consisting of a compact bilinear encoder and a compact multi-modal decoder, to improve image captioning with fine-grained regional object features. In the encoder, compact bilinear pooling (CBP) is used to encode fine-grained semantic features from an image’s regional features and transformers are used to encode global semantic features from an image’s global bottom-up features; the collective encoded features are subsequently fused using a gate structure to form the overall encoded features of the image. In the decoding process, we extract multi-modal features from fine grained regional object features, and fuse them with overall encoded features to decode semantic information for description generation. Extensive experiments performed on the public Microsoft COCO dataset show that our model achieves state-of-the-art image captioning performance.
    Reference | Related Articles | Metrics
    Methods and progress in deep neural network model compression
    LAI Yejing, HAO Shanfeng, HUANG Dingjiang
    Journal of East China Normal University(Natural Science)    2020, 2020 (5): 68-82.   DOI: 10.3969/j.issn.1000-5641.202091001
    Abstract （464）   HTML （49）    PDF （1132KB）（290）      
    The deep neural network (DNN) model achieves strong performance using substantial memory consumption and high computational power, which can be difficult to deploy on hardware platforms with limited resources. To meet these challenges, researchers have made great strides in this field and have formed a wealth of relevant literature and methods. This paper introduces four representative compression methods for deep neural networks used in recent years: network pruning, quantization, knowledge distillation, and compact network design; in particular, the article focuses on the characteristics of these representative models. Finally, evaluation criteria and research prospects of model compression are summarized.
    Reference | Related Articles | Metrics