• Computers and Concrete
• /
• v.26 no.5
• /
• pp.411-420
• /
• 2020

Deep Convolution neural network (DCNN) has been widely used in the healthy maintenance of civil infrastructure. Using DCNN to improve crack detection performance has attracted many researchers' attention. In this paper, a light-weight spatial attention network module is proposed to strengthen the representation capability of ResNet and improve the crack detection performance. It utilizes attention mechanism to strengthen the interested objects in global receptive field of ResNet convolution layers. Global average spatial information over all channels are used to construct an attention scalar. The scalar is combined with adaptive weighted sigmoid function to activate the output of each channel's feature maps. Salient objects in feature maps are refined by the attention scalar. The proposed spatial attention module is stacked in ResNet50 to detect crack. Experiments results show that the proposed module can got significant performance improvement in crack detection.

• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.15-22
• /
• 2020

In this paper, we proposed a deep learning based super-resolution method that combines Channel Attention and Spatial Attention feature enhancement methods. It is important to restore high-frequency components, such as texture and features, that have large changes in surrounding pixels during super-resolution processing. We proposed a super-resolution method using feature enhancement that combines Channel Attention and Spatial Attention. The existing CNN (Convolutional Neural Network) based super-resolution method has difficulty in deep network learning and lacks emphasis on high frequency components, resulting in blurry contours and distortion. In order to solve the problem, we used an emphasis block that combines Channel Attention and Spatial Attention to which Skip Connection was applied, and a Residual Block. The emphasized feature map extracted by the method was extended through Sub-pixel Convolution to obtain the super resolution. As a result, about PSNR improved by 5%, SSIM improved by 3% compared with the conventional SRCNN, and by comparison with VDSR, about PSNR improved by 2% and SSIM improved by 1%.

• Korean Journal of Cognitive Science
• /
• v.34 no.1
• /
• pp.1-20
• /
• 2023

In this study, we examined the effects of spatial attention in Hangul word recognition depending on visual factors. The visual complexity of words (Experiment 1) and contrast (Experiment 2) were manipulated to examine whether the effect of spatial attention differs depending on visual quality. Participants responded to words with and without codas in experiment 1 and words in high-contrast and low-contrast conditions in experiment 2. The effects of spatial attention were investigated by calculating the difference in performance between the condition where spatial cues were given at the target location (valid trial) and the condition where the spatial cues were not given at the target location (invalid trial) as the cuing effects. As a result, the cuing effects were similar depending on the complexity of the words. It indicates that the effects of spatial attention were not different across the visual complexity conditions. The cuing effects were greater in the low-contrast condition than in the high-contrast condition. The greater effect of spatial attention when the contrast is low was explained as a mechanism of signal enhancement.

• Korean Journal of Cognitive Science
• /
• v.19 no.2
• /
• pp.125-142
• /
• 2008

This study investigated the effects of space- and object-based attention on spatial and visual working memory, by measuring recognition of working memory on the spatial Stroop task including two modalities of attention resource. The similarity condition of stimulus arrangement between working memory task and spatial stroop task was manipulated in order to examine the effects of space-based attention on spatial rehearsal during working memory task, while Stroop rendition was manipulated in order to examine the effects of object-based attention on object rehearsal during working memory task. The results showed that in a condition that stimulus arrangement was highly similar for the spatial working memory task and the spatial Stroop task, recognition accuracy of the spatial working memory was high, but it was not significantly different with the Stroop conditions. In contrast, the recognition accuracy of visual working memory in the incongruent Stroop condition was lower than that in the congruent Stroop condition, but it was not significantly different with the similarity conditions (25% vs. 75%). The results indicated that selective attention has effects on working memory only when resource modality of working memory is the same as that of selective attention.

• Korean Journal of Cognitive Science
• /
• v.11 no.3_4
• /
• pp.13-22
• /
• 2000

The present study examined the role of spatial attention in implicit memory for words when the word identity processing was not required. Spatial attention to the identity-irrelevant perceptual features of the words was manipulated by using a visual search task (Experiment 1) or a focused attention task (Experiment 2). In two e experiments. a significant priming effect was not found for the target words as well as for the distractor words. Implicit memory for words was not affected by spatial attention on the perceptual properties of the words. indicating that the word identity processing is required to produce priming.

• Journal of the Korea Convergence Society
• /
• v.12 no.12
• /
• pp.31-37
• /
• 2021

In this paper proposed a feature fusion and spatial attention-based modified YOLOv4S for small and occluded detection. Conventional YOLOv4S is a lightweight network and lacks feature extraction capability compared to the method of the deep network. The proposed method first combines feature maps of different scales with feature fusion to enhance semantic and low-level information. In addition expanding the receptive field with dilated convolution, the detection accuracy for small and occluded objects was improved. Second by improving the conventional spatial information with spatial attention, the detection accuracy of objects classified and occluded between objects was improved. PASCAL VOC and COCO datasets were used for quantitative evaluation of the proposed method. The proposed method improved mAP by 2.7% in the PASCAL VOC dataset and 1.8% in the COCO dataset compared to the Conventional YOLOv4S.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.37-46
• /
• 2020

Recently, studies of facial attribute editing have obtained realistic results using generative adversarial net (GAN) and encoder-decoder structure. Spatial attention GAN (SaGAN), one of the latest researches, is the method that can change only desired attribute in a face image by spatial attention mechanism. However, sometimes unnatural results are obtained due to insufficient information on face areas. In this paper, we propose an improved SaGAN (MSaGAN) using a guide mask for learning and applying multitask learning approach to improve the limitations of the existing methods. Through extensive experiments, we evaluated the results of the facial attribute editing in therms of the mask loss function and the neural network structure. It has been shown that the proposed method can efficiently produce more natural results compared to the previous methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3685-3707
• /
• 2021

In recent years, facial attribute editing has been successfully used to effectively change face images of various attributes based on generative adversarial networks and encoder-decoder models. However, existing models have a limitation in that they may change an unintended part in the process of changing an attribute or may generate an unnatural result. In this paper, we propose a model that improves the learning of the attention mask by adding a spatial attention mechanism based on the unified selective transfer network (referred to as STGAN) using semi-supervised learning. The proposed model can edit multiple attributes while preserving details independent of the attributes being edited. This study makes two main contributions to the literature. First, we propose an encoder-decoder model structure that learns and edits multiple facial attributes and suppresses distortion using an attention mask. Second, we define guide masks and propose a method and an objective function that use the guide masks for multiple facial attribute editing through semi-supervised learning. Through qualitative and quantitative evaluations of the experimental results, the proposed method was proven to yield improved results that preserve the image details by suppressing unintended changes than existing methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• pp.2361-2376
• /
• 2023

The electrocardiogram (ECG) signal is commonly used to screen and diagnose cardiovascular diseases. In recent years, deep neural networks have been regarded as an effective way for automatic ECG disease diagnosis. The convolutional neural network is widely used for ECG signal extraction because it can obtain different levels of information. However, most previous studies adopt single scale convolution filters to extract ECG signal features, ignoring the complementarity between ECG signal features of different scales. In the paper, we propose a dual-scale network with convolution filters of different sizes for 12-lead ECG classification. Our model can extract and fuse ECG signal features of different scales. In addition, different spatial and time periods of the feature map obtained from the 12-lead ECG may have different contributions to ECG classification. Therefore, we add a spatial-temporal attention to each scale sub-network to emphasize the representative local spatial and temporal features. Our approach is evaluated on PTB-XL dataset and achieves 0.9307, 0.8152, and 89.11 on macro-averaged ROC-AUC score, a maximum F1 score, and mean accuracy, respectively. The experiment results have proven that our approach outperforms the baselines.

• Korean Journal of Cognitive Science
• /
• v.19 no.3
• /
• pp.311-330
• /
• 2008

The effect of spatial attention gradually decreases as a function of the distance between the locus of attention and a target. According to this hypothesis, we tested the spatial-effect profile of visual attention when it operates on perception and memory. Experiment 1 measured accuracy of discriminating the color of a simultaneously masked target after presenting a pre-cue to either at the target location or away from the target (perception-intensive task). Experiment 2 measured accuracy of recognizing the color of several items at and around the pre-cued location (memory-intensive task). In the perception-intensive condition, the accuracy gradually dropped as the distance between the cue and target location increases. However, in the memory-intensive condition, subjects remembered only the item at the cued location. This suggests spatial attention in a memory-intensive process would operate on object-based representations. Experiment 2 showed the object-based effect observed in Experiment 1 can be also present in perception under a special circumstance. The results indicate that spatial attention can operate on object-based representations in a memory-intensive process whereas it flexibly can operate either on location-based or object-based representations in a perception-intensive process.