Feedback LSTM Network Based on Attention for Image Description Generator

Images are complex multimedia data which contain rich semantic information.Most of current image description generator algorithms only generate plain description,with the lack of distinction between primary and secondary object,leading to insufficient high-level semantic and accuracy under public evaluation criteria.The major issue is the lack of effective network on high-level semantic sentences generation,which contains detailed description for motion and state of the principal object.To address the issue,this paper proposes the Attention-based Feedback Long Short-Term Memory Network(AFLN).Based on existing codec framework,there are two independent sub tasks in our method:attention-based feedback LSTM network during decoding and the Convolutional Block Attention Module(CBAM)in the coding phase.First,we propose an attentionbased network to feedback the features corresponding to the generated word from the previous LSTM decoding unit.We implement feedback guidance through the related field mapping algorithm,which quantifies the correlation between previous word and latter word,so that the main object can be tracked with highlighted detailed description.Second,we exploit the attention idea and apply a lightweight and general module called CBAM after the last layer of VGG 16 pretraining network,which can enhance the expression of image coding features by combining channel and spatial dimension attention maps with negligible overheads.Extensive experiments on COCO dataset validate the superiority of our network over the state-of-the-art algorithms.Both scores and actual effects are proved.The BLEU 4 score increases from 0.291 to 0.301 while the CIDEr score rising from 0.912 to 0.952.

An Approach to Modelling and Analysing Reliability of Breeze/ADL-based Software Architecture

Breeze/architecture description language（ADL）, is an eX tensible markup language（XML） based architecture description language which is used to model software systems at the architecture level. Though Breeze/ADL provides an appropriate basis for architecture modelling, it can neither analyse nor evaluate the architecture reliability. In this paper, we propose a Breeze/ADL based strategy which, by combining generalized stochastic Petri net（GSPN） and tools for reliability analysis, supports architecture reliability modelling and evaluation. This work expands the idea in three directions： Firstly, we give a Breeze/ADL reliability model in which we add error attributes to Breeze/ADL error model for capturing architecture error information, and at the same time perform the system error state transition through the Breeze/ADL production. Secondly, we present how to map a Breeze/ADL reliability model to a GSPN model, which in turn can be used for reliability analysis. The other task is to develop a Breeze/ADL reliability analysis modelling tool–EXGSPN（Breeze/ADL reliability analysis modelling tool）, and combine it with platform independent petri net editor 2（PIPE2） to carry out a reliability assessment.Abstract： Breeze/architecture description language （ADL）, is an eXtensible markup language （XML） based architecture description language which is used to model software systems at the architecture level. Though Breeze/ADL provides an appropriate basis for architecture modelling, it can neither analyse nor evaluate the architecture reliability. In this paper, we propose a Breeze/ADL based strategy which, by combining generalized stochastic Petri net （GSPN） and tools for reliability analysis, supports architecture reliability modelling and evaluation. This work expands the idea in three directions： Firstly, we give a Breeze/ADL reliability model in which we add error attributes to Breeze/ADL error model for capturing architecture error information, and at the same time perform the system error state transition through the Breeze/ADL production. Secondly, we present how to map a Breeze/ADL reliability model to a GSPN model, which in turn can be used for reliability analysis. The other task is to develop a Breeze/ADL reliability analysis modelling tool-EXGSPN （Breeze/ADL reliability analysis modelling tool）, and combine it with platform independent petri net editor 2 （PIPE2） to carry out a reliability assessment.