The automatic defect detection for fabric images is an essential mission in textile industry. However, there are some inherent difficulties in the detection of fabric images, such as complexity of the background and the highly uneven scales of defects. Moreover, the trade-off between accuracy and speed should be considered in real applications. To address these problems, we propose a novel model based on YOLOv4 to detect defects in fabric images, called Feature Augmentation YOLO (FA-YOLO). In terms of network structure, FA-YOLO adds an additional detection head to improve the detection ability of small defects and builds a powerful Neck structure to enhance feature fusion. First, to reduce information loss during feature fusion, we perform the residual feature augmentation (RFA) on the features after dimensionality reduction by using 1×1 convolution. Afterward, the attention module (SimAM) is embedded into the locations with rich features to improve the adaptation ability to complex backgrounds. Adaptive spatial feature fusion (ASFF) is also applied to output of the Neck to filter inconsistencies across layers. Finally, the cross-stage partial (CSP) structure is introduced for optimization. Experimental results based on three real industrial datasets, including Tianchi fabric dataset (72.5% mAP), ZJU-Leaper fabric dataset (0.714 of average F1-score) and NEU-DET steel dataset (77.2% mAP), demonstrate the proposed FA-YOLO achieves competitive results compared to other state-of-the-art (SoTA) methods.

This paper investigates the effects of backdoor attacks on graph neural networks (GNNs) trained through simple data augmentation by modifying the edges of the graph in graph classification. The numerical results show that GNNs trained with data augmentation remain vulnerable to backdoor attacks and may even be more vulnerable to such attacks than GNNs without data augmentation.

We investigated the influence of horizontal shifts of the input images for one stage object detection method. We found that the object detector class scores drop when the target object center is at the grid boundary. Many approaches have focused on reducing the aliasing effect of down-sampling to achieve shift-invariance. However, down-sampling does not completely solve this problem at the grid boundary; it is necessary to suppress the dispersion of features in pixels close to the grid boundary into adjacent grid cells. Therefore, this paper proposes two approaches focused on the grid boundary to improve this weak point of current object detection methods. One is the Sub-Grid Feature Extraction Module, in which the sub-grid features are added to the input of the classification head. The other is Grid-Aware Data Augmentation, where augmented data are generated by the grid-level shifts and are used in training. The effectiveness of the proposed approaches is demonstrated using the COCO validation set after applying the proposed method to the FCOS architecture.

We present an effective system for integrating generative zero-shot classification modules into a YOLO-like dense detector to detect novel objects. Most double-stage-based novel object detection methods are achieved by refining the classification output branch but cannot be applied to a dense detector. Our system utilizes two paths to inject knowledge of novel objects into a dense detector. One involves injecting the class confidence for novel classes from a classifier trained on data synthesized via a dual-step generator. This generator learns a mapping function between two feature spaces, resulting in better classification performance. The second path involves re-training the detector head with feature maps synthesized on different intensity levels. This approach significantly increases the predicted objectness for novel objects, which is a major challenge for a dense detector. We also introduce a stop-and-reload mechanism during re-training for optimizing across head layers to better learn synthesized features. Our method relaxes the constraint on the detector head architecture in the previous method and has markedly enhanced performance on the MSCOCO dataset.

High-performance deep learning-based object detection models can reduce traffic accidents using dashcam images during nighttime driving. Deep learning requires a large-scale dataset to obtain a high-performance model. However, existing object detection datasets are mostly daytime scenes and a few nighttime scenes. Increasing the nighttime dataset is laborious and time-consuming. In such a case, it is possible to convert daytime images to nighttime images by image-to-image translation model to augment the nighttime dataset with less effort so that the translated dataset can utilize the annotations of the daytime dataset. Therefore, in this study, a GAN-based image-to-image translation model is proposed by incorporating self-attention with cycle consistency and content/style separation for nighttime data augmentation that shows high fidelity to annotations of the daytime dataset. Experimental results highlight the effectiveness of the proposed model compared with other models in terms of translated images and FID scores. Moreover, the high fidelity of translated images to the annotations is verified by a small object detection model according to detection results and mAP. Ablation studies confirm the effectiveness of self-attention in the proposed model. As a contribution to GAN-based data augmentation, the source code of the proposed image translation model is publicly available at https://github.com/subecky/Image-Translation-With-Self-Attention

In machine learning, data augmentation (DA) is a technique for improving the generalization performance of models. In this paper, we mainly consider gradient descent of linear regression under DA using noisy copies of datasets, in which noise is injected into inputs. We analyze the situation where noisy copies are newly generated and injected into inputs at each epoch, i.e., the case of using on-line noisy copies. Therefore, this article can also be viewed as an analysis on a method using noise injection into a training process by DA. We considered the training process under three training situations which are the full-batch training under the sum of squared errors, and full-batch and mini-batch training under the mean squared error. We showed that, in all cases, training for DA with on-line copies is approximately equivalent to the l2 regularization training for which variance of injected noise is important, whereas the number of copies is not. Moreover, we showed that DA with on-line copies apparently leads to an increase of learning rate in full-batch condition under the sum of squared errors and the mini-batch condition under the mean squared error. The apparent increase in learning rate and regularization effect can be attributed to the original input and additive noise in noisy copies, respectively. These results are confirmed in a numerical experiment in which we found that our result can be applied to usual off-line DA in an under-parameterization scenario and can not in an over-parametrization scenario. Moreover, we experimentally investigated the training process of neural networks under DA with off-line noisy copies and found that our analysis on linear regression can be qualitatively applied to neural networks.

Medical images play an important role in medical diagnosis. However, acquiring a large number of datasets with annotations is still a difficult task in the medical field. For this reason, research in the field of image-to-image translation is combined with computer-aided diagnosis, and data augmentation methods based on generative adversarial networks are applied to medical images. In this paper, we try to perform data augmentation on unimodal data. The designed StarGAN V2 based network has high performance in augmenting the dataset using a small number of original images, and the augmented data is expanded from unimodal data to multimodal medical images, and this multimodal medical image data can be applied to the segmentation task with some improvement in the segmentation results. Our experiments demonstrate that the generated multimodal medical image data can improve the performance of glioma segmentation.

The data augmentation method is known as a helpful technique to generate a dataset with a large number of images from one with a small number of images for supervised training in deep learning. However, a low validity augmentation method for image recognition was reported in a recent study on artificial intelligence (AI). This study aimed to clarify the optimal data augmentation method in deep learning model generation for the recognition of white blood cells (WBCs). Study Design: We conducted three different data augmentation methods (rotation, scaling, and distortion) on original WBC images, with each AI model for WBC recognition generated by supervised training. The subjects of the clinical assessment were 51 healthy persons. Thin-layer blood smears were prepared from peripheral blood and subjected to May-Grünwald-Giemsa staining. Results: The only significantly effective technique among the AI models for WBC recognition was data augmentation with rotation. By contrast, the effectiveness of both image distortion and image scaling was poor, and improved accuracy was limited to a specific WBC subcategory. Conclusion: Although data augmentation methods are often used for achieving high accuracy in AI generation with supervised training, we consider that it is necessary to select the optimal data augmentation method for medical AI generation based on the characteristics of medical images.

Fault localization analyzes the runtime information of two classes of test cases (i.e., passing test cases and failing test cases) to identify suspicious statements potentially responsible for a failure. However, the failing test cases are always far fewer than passing test cases in reality, and the class imbalance problem will affect fault localization effectiveness. To address this issue, we propose a data augmentation approach using conditional variational auto-encoder to synthesize new failing test cases for FL. The experimental results show that our approach significantly improves six state-of-the-art fault localization techniques.

Visible-Infrared Person Re-identification (VI-ReID) is a challenging pedestrian retrieval task due to the huge modality discrepancy and appearance discrepancy. To address this tough task, this letter proposes a novel gray augmentation exploration (GAE) method to increase the diversity of training data and seek the best ratio of gray augmentation for learning a more focused model. Additionally, we also propose a strong all-modality center-triplet (AMCT) loss to push the features extracted from the same pedestrian more compact but those from different persons more separate. Experiments conducted on the public dataset SYSU-MM01 demonstrate the superiority of the proposed method in the VI-ReID task.

Incremental Learning, a machine learning methodology, trains the continuously arriving input data and extends the model's knowledge. When it comes to unlabeled data streams, incremental learning task becomes more challenging. Our newly proposed incremental learning methodology, Data Augmented Incremental Learning (DAIL), learns the ever-increasing real-time streams with reduced memory resources and time. Initially, the unlabeled batches of data streams are clustered using the proposed clustering algorithm, Clustering based on Autoencoder and Gaussian Model (CLAG). Later, DAIL creates an updated incremental model for the labelled clusters using data augmentation. DAIL avoids the retraining of old samples and retains only the most recently updated incremental model holding all old class information. The use of data augmentation in DAIL combines the similar clusters generated with different data batches. A series of experiments verified the significant performance of CLAG and DAIL, producing scalable and efficient incremental model.

As the mainstream approach in the field of machine translation, neural machine translation (NMT) has achieved great improvements on many rich-source languages, but performance of NMT for low-resource languages ae not very good yet. This paper uses data enhancement technology to construct Mongolian-Chinese pseudo parallel corpus, so as to improve the translation ability of Mongolian-Chinese translation model. Experiments show that the above methods can improve the translation ability of the translation model. Finally, a translation model trained with large-scale pseudo parallel corpus and integrated with soft context data enhancement technology is obtained, and its BLEU value is 39.3.

Recently, local features computed using convolutional neural networks (CNNs) show good performance to image retrieval. The local convolutional features obtained by the CNNs (LC features) are designed to be translation invariant, however, they are inherently sensitive to rotation perturbations. This leads to miss-judgements in retrieval tasks. In this work, our objective is to enhance the robustness of LC features against image rotation. To do this, we conduct a thorough experimental evaluation of three candidate anti-rotation strategies (in-model data augmentation, in-model feature augmentation, and post-model feature augmentation), over two kinds of rotation attack (dataset attack and query attack). In the training procedure, we implement a data augmentation protocol and network augmentation method. In the test procedure, we develop a local transformed convolutional (LTC) feature extraction method, and evaluate it over different network configurations. We end up a series of good practices with steady quantitative supports, which lead to the best strategy for computing LC features with high rotation invariance in image retrieval.

Since a concept can be represented by different vocabularies, styles, and levels of detail, a translation task resembles a many-to-many mapping task from a distribution of sentences in the source language into a distribution of sentences in the target language. This viewpoint, however, is not fully implemented in current neural machine translation (NMT), which is one-to-one sentence mapping. In this study, we represent the distribution itself as multiple paraphrase sentences, which will enrich the model context understanding and trigger it to produce numerous hypotheses. We use a visually grounded paraphrase (VGP), which uses images as a constraint of the concept in paraphrasing, to guarantee that the created paraphrases are within the intended distribution. In this way, our method can also be considered as incorporating image information into NMT without using the image itself. We implement this idea by crowdsourcing a paraphrasing corpus that realizes VGP and construct neural paraphrasing that behaves as expert models in a NMT. Our experimental results reveal that our proposed VGP augmentation strategies showed improvement against a vanilla NMT baseline.

The natural gradient descent is an optimization method for real-valued neural networks that was proposed from the viewpoint of information geometry. Here, we present an extension of the natural gradient descent to complex-valued neural networks. Our idea is to use the Hermitian extension of the Fisher information matrix. Moreover, we generalize the projected natural gradient (PRONG), which is a fast natural gradient descent algorithm, to complex-valued neural networks. We also consider the advantage of complex-valued neural networks over real-valued neural networks. A useful property of complex numbers in the complex plane is that the rotation is simply expressed by the multiplication. By focusing on this property, we construct the output function of complex-valued neural networks, which is invariant even if the input is changed to its rotated value. Then, our complex-valued neural network can learn rotated data without data augmentation. Finally, through simulation of online character recognition, we demonstrate the effectiveness of the proposed approach.

The k-edge-connectivity augmentation problem for a specified set of vertices (kECA-SV for short) is defined by “Given a graph G=(V, E) and a subset Γ ⊆ V, find a minimum set E' of edges such that G'=(V, E ∪ E') has at least k edge-disjoint paths between any pair of vertices in Γ.” Let σ be the edge-connectivity of Γ (that is, G has at least σ edge-disjoint paths between any pair of vertices in Γ). We propose an algorithm for (σ+1)ECA-SV which is done in O(|Γ|) maximum flow operations. Then the time complexity is O(σ2|Γ||V|+|E|) if a given graph is sparse, or O(|Γ||V||BG|log(|V|2/|BG|)+|E|) if dense, where |BG| is the number of pairs of adjacent vertices in G. Also mentioned is an O(|V||E|+|V|2 log |V|) time algorithm for a special case where σ is equal to the edge-connectivity of G and an O(|V|+|E|) time one for σ ≤ 2.

The number of infected hosts on enterprise networks has been increased by drive-by download attacks. In these attacks, users of compromised popular websites are redirected toward websites that exploit vulnerabilities of a browser and its plugins. To prevent damage, detection of infected hosts on the basis of proxy logs rather than blacklist-based filtering has started to be researched. This is because blacklists have become difficult to create due to the short lifetime of malicious domains and concealment of exploit code. To detect accesses to malicious websites from proxy logs, we propose a system for detecting malicious URL sequences on the basis of three key ideas: focusing on sequences of URLs that include artifacts of malicious redirections, designing new features related to software other than browsers, and generating new training data with data augmentation. To find an effective approach for classifying URL sequences, we compared three approaches: an individual-based approach, a convolutional neural network (CNN), and our new event de-noising CNN (EDCNN). Our EDCNN reduces the negative effects of benign URLs redirected from compromised websites included in malicious URL sequences. Evaluation results show that only our EDCNN with proposed features and data augmentation achieved a practical classification performance: a true positive rate of 99.1%, and a false positive rate of 3.4%.

We present a new action classification method for skeletal sequence data. The proposed method is based on simple nonparametric feature matching without a learning process. We first augment the training dataset to implicitly construct an exponentially increasing number of training sequences, which can be used to improve the generalization power of the proposed action classifier. These augmented training sequences are matched to the test sequence with the relaxed dynamic time warping (DTW) technique. Our relaxed formulation allows the proposed method to work faster and with higher efficiency than the conventional DTW-based method using a non-augmented dataset. Experimental results show that the proposed approach produces effective action classification results for various scales of real datasets.

The k-edge-connectivity augmentation problem with multipartition constraints (kECAMP, for short) is defined by “Given a multigraph G=(V,E) and a multipartition π={V1,...,Vr} (r≥2) of V, that is, $V = igcup_{h = 1}^r V_h$ and Vi∩Vj=∅ (1≤i

A non-linear extension of generalized hyperplane approximation (GHA) method is introduced in this letter. Although GHA achieved a high-confidence result in motion parameter estimation by utilizing the supervised learning scheme in histogram of oriented gradient (HOG) feature space, it still has unstable convergence range because it approximates the non-linear function of regression from the feature space to the motion parameter space as a linear plane. To extend GHA into a non-linear regression for larger convergence range, we derive theoretical equations and verify this extension's effectiveness and efficiency over GHA by experimental results.