Intelligent Detection of Steel Defects Based on Improved Split Attention Networks

The intelligent monitoring and diagnosis of steel defects plays an important role in improving steel quality, production efficiency, and associated smart manufacturing. The application of the bio-inspired algorithms to mechanical engineering problems is of great significance. The split attention network is an improvement of the residual network, and it is an improvement of the visual attention mechanism in the bionic algorithm. In this paper, based on the feature pyramid network and split attention network, the network is improved and optimised in terms of data enhancement, multi-scale feature fusion and network structure optimisation. The DF-ResNeSt50 network model is proposed, which introduces a simple modularized split attention block, which can improve the attention mechanism of cross-feature graph groups. Finally, experimental validation proves that the proposed network model has good performance and application prospects in the intelligent detection of steel defects.

A 3D Keypoints Voting Network for 6DoF Pose Estimation in Indoor Scene

This paper addresses the problem of instance-level 6DoF pose estimation from a single RGBD image in an indoor scene. Many recent works have shown that a two-stage network, which first detects the keypoints and then regresses the keypoints for 6d pose estimation, achieves remarkable performance. However, the previous methods concern little about channel-wise attention and the keypoints are not selected by comprehensive use of RGBD information, which limits the performance of the network. To enhance RGB feature representation ability, a modular Split-Attention block that enables attention across feature-map groups is proposed. In addition, by combining the Oriented FAST and Rotated BRIEF (ORB) keypoints and the Farthest Point Sample (FPS) algorithm, a simple but effective keypoint selection method named ORB-FPS is presented to avoid the keypoints appear on the non-salient regions. The proposed algorithm is tested on the Linemod and the YCB-Video dataset, the experimental results demonstrate that our method outperforms the current approaches, achieves ADD(S) accuracy of 94.5% on the Linemod dataset and 91.4% on the YCB-Video dataset.

Split-Attention Networks with Self-Calibrated Convolution for Moon Impact Crater Detection from Multi-Source Data

Impact craters are the most prominent features on the surface of the Moon, Mars, and Mercury. They play an essential role in constructing lunar bases, the dating of Mars and Mercury, and the surface exploration of other celestial bodies. The traditional crater detection algorithms (CDA) are mainly based on manual interpretation which is combined with classical image processing techniques. The traditional CDAs are, however, inefficient for detecting smaller or overlapped impact craters. In this paper, we propose a Split-Attention Networks with Self-Calibrated Convolution (SCNeSt) architecture, in which the channel-wise attention with multi-path representation and self-calibrated convolutions can generate more prosperous and more discriminative feature representations. The algorithm first extracts the crater feature model under the well-known target detection R-FCN network framework. The trained models are then applied to detecting the impact craters on Mercury and Mars using the transfer learning method. In the lunar impact crater detection experiment, we managed to extract a total of 157,389 impact craters with diameters between 0.6 and 860 km. Our proposed model outperforms the ResNet, ResNeXt, ScNet, and ResNeSt models in terms of recall rate and accuracy is more efficient than that other residual network models. Without training for Mars and Mercury remote sensing data, our model can also identify craters of different scales and demonstrates outstanding robustness and transferability.

Strategi meminimalkan beban kognitif eksternal dalam pembelajaran matematika berdasarkan load cognitive theory

Memahami objek, konsep, prosedur merupakan salah satu tujuan mempelajari pelajaran matematika disekolah. Muatan materi yang cendrung kompleks dengan elemen-elemen yang abstrak menjadi masalah bagi siswa sehingga memunculkan beban kognitif, diantaranya adalah beban kognitif eksternal. Tujuan dari penelitian ini untuk menunjukkan beberapa strategi yang perlu diperhatikan dalam mendesain pembelajaran matematika agar dapat meminimalkan beban kognitif eksternal. Penelitian ini berupa studi kepustakaan (library research). Teknik pengumpulan data dalam penelitian ini, dilakukan dengan melakukan penelusuran referensi secara online melalui beberapa sumber basis data Google Cendikia, ERIC Institute of Education Science, serta Science Direct. Analisis data dalam penelitian ini menggunakan metode analisis isi (content analysis). Hasil kajian dalam studi ini terdapat 8 strategi dalam mendesain pembelajaran matematika untuk meminimalkan beban kognitif eksternal diantaranya The Goal-Free Effect, The Worked Exampel Effect, The Split-Attention Effect, The Modality Effect, The Redundancy Effect, The Element Interactivity Effect, The Imagination Effect dan The Guidance Fading Effect.Understanding objects, concepts, procedures is one of the goals of studying mathematics in school. Material content that tends to be complex with abstract elements becomes a problem for students so that it creates cognitive loads, including external cognitive loads. The purpose of this study is to show several strategies that need to be considered in designing mathematics learning in order to minimize external cognitive load. This research is in the form of library research (library research). The data collection technique in this study was carried out by searching for references online through several Google Cendikia database sources, ERIC Institute of Education Science, and Science Direct. Analysis of the data in this study using content analysis method. The results of the study in this study there are 8 strategies in designing mathematics learning to minimize external cognitive load including The Goal-Free Effect, The Worked Exampel Effect, The Split-Attention Effect, The Modality Effect, The Redundancy Effect, The Element Interactivity Effect, The Imagination Effect and The Guidance Fading Effect.