Tomáš Horváth

Dániel Horváth, Gábor Erdős, Zoltán Istenes et al.

Robots working in unstructured environments must be capable of sensing and interpreting their surroundings. One of the main obstacles of deep-learning-based models in the field of robotics is the lack of domain-specific labeled data for different industrial applications. In this article, we propose a sim2real transfer learning method based on domain randomization for object detection with which labeled synthetic datasets of arbitrary size and object types can be automatically generated. Subsequently, a state-of-the-art convolutional neural network, YOLOv4, is trained to detect the different types of industrial objects. With the proposed domain randomization method, we could shrink the reality gap to a satisfactory level, achieving 86.32% and 97.38% mAP50 scores, respectively, in the case of zero-shot and one-shot transfers, on our manually annotated dataset containing 190 real images. Our solution fits for industrial use as the data generation process takes less than 0.5 s per image and the training lasts only around 12 h, on a GeForce RTX 2080 Ti GPU. Furthermore, it can reliably differentiate similar classes of objects by having access to only one real image for training. To our best knowledge, this is the only work thus far satisfying these constraints.

Sofiane Ouaari, Tsegaye Misikir Tashu, Tomas Horvath

In this study, we propose feature extraction for multimodal meme classification using Deep Learning approaches. A meme is usually a photo or video with text shared by the young generation on social media platforms that expresses a culturally relevant idea. Since they are an efficient way to express emotions and feelings, a good classifier that can classify the sentiment behind the meme is important. To make the learning process more efficient, reduce the likelihood of overfitting, and improve the generalizability of the model, one needs a good approach for joint feature extraction from all modalities. In this work, we proposed to use different multimodal neural network approaches for multimodal feature extraction and use the extracted features to train a classifier to identify the sentiment in a meme.

Tsegaye Misikir Tashu, Chandresh Kumar Maurya, Tomas Horvath

Automatic evaluation of essay (AES) and also called automatic essay scoring has become a severe problem due to the rise of online learning and evaluation platforms such as Coursera, Udemy, Khan academy, and so on. Researchers have recently proposed many techniques for automatic evaluation. However, many of these techniques use hand-crafted features and thus are limited from the feature representation point of view. Deep learning has emerged as a new paradigm in machine learning which can exploit the vast data and identify the features useful for essay evaluation. To this end, we propose a novel architecture based on recurrent networks (RNN) and convolution neural network (CNN). In the proposed architecture, the multichannel convolutional layer learns and captures the contextual features of the word n-gram from the word embedding vectors and the essential semantic concepts to form the feature vector at essay level using max-pooling operation. A variant of RNN called Bi-gated recurrent unit (BGRU) is used to access both previous and subsequent contextual representations. The experiment was carried out on eight data sets available on Kaggle for the task of AES. The experimental results show that our proposed system achieves significantly higher grading accuracy than other deep learning-based AES systems and also other state-of-the-art AES systems.

Tsegaye Misikir Tashu, Sara Fattouh, Peter Kiss et al.

In this work, we present a multi-modal model for commercial product classification, that combines features extracted by multiple neural network models from textual (CamemBERT and FlauBERT) and visual data (SE-ResNeXt-50), using simple fusion techniques. The proposed method significantly outperformed the unimodal models' performance and the reported performance of similar models on our specific task. We did experiments with multiple fusing techniques and found, that the best performing technique to combine the individual embedding of the unimodal network is based on combining concatenation and averaging the feature vectors. Each modality complemented the shortcomings of the other modalities, demonstrating that increasing the number of modalities can be an effective method for improving the performance of multi-label and multimodal classification problems.

Ermiyas Birihanu, Jiyan Mahmud, Péter Kiss et al.

Content delivery networks (CDNs) are the backbone of the Internet and are key in delivering high quality video on demand (VoD), web content and file services to billions of users. CDNs usually consist of hierarchically organized content servers positioned as close to the customers as possible. CDN operators face a significant challenge when analyzing billions of web server and proxy logs generated by their systems. The main objective of this study was to analyze the applicability of various clustering methods in CDN error log analysis. We worked with real-life CDN proxy logs, identified key features included in the logs (e.g., content type, HTTP status code, time-of-day, host) and clustered the log lines corresponding to different host types offering live TV, video on demand, file caching and web content. Our experiments were run on a dataset consisting of proxy logs collected over a 7-day period from a single, physical CDN server running multiple types of services (VoD, live TV, file). The dataset consisted of 2.2 billion log lines. Our analysis showed that CDN error clustering is a viable approach towards identifying recurring errors and improving overall quality of service.