Metallic surface defect detection is an essential and necessary process to control the qualities of industrial products. However, due to the limited data scale and defect categories, existing defect datasets are generally unavailable for the deployment of the detection model. To address this problem, we contribute a new dataset called GC10-DET for large-scale metallic surface defect detection. The GC10-DET dataset has great challenges on defect categories, image number, and data scale. Besides, traditional detection approaches are poor in both efficiency and accuracy for the complex real-world environment. Thus, we also propose a novel end-to-end defect detection network (EDDN) based on the Single Shot MultiBox Detector. The EDDN model can deal with defects with different scales. Furthermore, a hard negative mining method is designed to alleviate the problem of data imbalance, while some data augmentation methods are adopted to enrich the training data for the expensive data collection problem. Finally, the extensive experiments on two datasets demonstrate that the proposed method is robust and can meet accuracy requirements for metallic defect detection.
Surface defect detection of products is an important process to guarantee the quality of industrial production. A defect detection task aims to identify the specific category and precise position of defect in an image. It is hard to take into account the accuracy of both, which makes it be challenging in practice. In this study, a new deep neural network (DNN), RetinaNet with difference channel attention and adaptively spatial feature fusion (DEA_RetinaNet), is proposed for steel surface defect detection. First, a differential evolution search-based anchor optimization is performed to improve the detection accuracy of DEA_RetinaNet. Second, a novel channel attention mechanism is embedded in DEA_RetinaNet to reduce information loss. Finally, the adaptive spatial feature fusion (ASFF) module is used for an effective fusion of shallow and deep features extracted by convolutional kernels. The experimental results on a steel surface defect data set (NEU-DET) show that DEA_RetinaNet achieved 78.25 mAP and improved by 2.92% over RetinaNet. It has better recognition performance compared with other famous DNN-based detectors.
We propose a single-stage Human-Object Interaction (HOI) detection method that has outperformed all existing methods on HICO-DET dataset at 37 fps on a single Titan XP GPU. It is the first real-time HOI detection method. Conventional HOI detection methods are composed of two stages, i.e., human-object proposals generation, and proposals classification. Their effectiveness and efficiency are limited by the sequential and separate architecture. In this paper, we propose a Parallel Point Detection and Matching (PPDM) HOI detection framework. In PPDM, an HOI is defined as a point triplet . Human and object points are the center of the detection boxes, and the interaction point is the midpoint of the human and object points. PPDM contains two parallel branches, namely point detection branch and point matching branch. The point detection branch predicts three points. Simultaneously, the point matching branch predicts two displacements from the interaction point to its corresponding human and object points. The human point and the object point originated from the same interaction point are considered as matched pairs. In our novel parallel architecture, the interaction points implicitly provide context and regularization for human and object detection. The isolated detection boxes unlikely to form meaningful HOI triplets are suppressed, which increases the precision of HOI detection. Moreover, the matching between human and object detection boxes is only applied around limited numbers of filtered candidate interaction points, which saves much computational cost. Additionally, we build a new application-oriented database named as HOI-A, which serves as a good supplement to the existing datasets.
We propose HOI Transformer to tackle human object interaction (HOI) detection in an end-to-end manner. Current approaches either decouple HOI task into separated stages of object detection and interaction classification or introduce surrogate interaction problem. In contrast, our method, named HOI Transformer, streamlines the HOI pipeline by eliminating the need for many hand-designed components. HOI Transformer reasons about the relations of objects and humans from global image context and directly predicts HOI instances in parallel. A quintuple matching loss is introduced to force HOI predictions in a unified way. Our method is conceptually much simpler and demonstrates improved accuracy. Without bells and whistles, HOI Transformer achieves 26.61% AP on HICO-DET and 52.9% AProle on V-COCO, surpassing previous methods with the advantage of being much simpler. We hope our approach will serve as a simple and effective alternative for HOI tasks. Code is available at https://github.com/bbepoch/HoiTransformer.
Drone captured images have overwhelming characteristics including dramatic scale variance, complicated background filled with distractors, and flexible viewpoints, which pose enormous challenges for general object detectors based on common convolutional networks. Recently, the design of vision backbone architectures that use self-attention is an exciting topic. In this work, an improved backbone MHSA-Darknet is designed to retain sufficient global context information and extract more differentiated features for object detection via multi-head self-attention. Regarding the path-aggregation neck, we present a simple yet highly effective weighted bi-directional feature pyramid network (BiFPN) for effectively cross-scale feature fusion. In addition, other techniques including time-test augmentation (TTA) and wighted boxes fusion (WBF) help to achieve better accuracy and robustness. Our experiments demonstrate that ViT-YOLO significantly outperforms the state-of-the-art detectors and achieve one of the top results in VisDrone-DET 2021 challenge (39.41 mAP for test-challenge data set and 41 mAP for the test-dev data set).
Recent years have witnessed rapid progress in detecting and recognizing individual object instances. To understand the situation in a scene, however, computers need to recognize how humans interact with surrounding objects. In this paper, we tackle the challenging task of detecting human-object interactions (HOI). Our core idea is that the appearance of a person or an object instance contains informative cues on which relevant parts of an image to attend to for facilitating interaction prediction. To exploit these cues, we propose an instance-centric attention module that learns to dynamically highlight regions in an image conditioned on the appearance of each instance. Such an attention-based network allows us to selectively aggregate features relevant for recognizing HOIs. We validate the efficacy of the proposed network on the Verb in COCO and HICO-DET datasets and show that our approach compares favorably with the state-of-the-arts.
Human-Object interaction (HOI) detection aims to localize and infer relationships between human and objects in an image. It is challenging because an enormous number of possible combinations of objects and verbs types forms a long-tail distribution. We devise a deep Visual Compositional Learning (VCL) framework, which is a simple yet efficient framework to effectively address this problem. VCL first decomposes an HOI representation into object and verb specific features, and then composes new interaction samples in the feature space via stitching the decomposed features. The integration of decomposition and composition enables VCL to share object and verb features among different HOI samples and images, and to generate new interaction samples and new types of HOI, and thus largely alleviates the long-tail distribution problem and benefits low-shot or zero-shot HOI detection. Extensive experiments demonstrate that the proposed VCL can effectively improve the generalization of HOI detection on HICO-DET and V-COCO and outperforms the recent state-of-the-art methods on HICO-DET. Code is available at this https URL.
The combinatorial problem of learning directed acyclic graphs (DAGs) from data was recently framed as a purely continuous optimization problem by leveraging a differentiable acyclicity characterization of DAGs based on the trace of a matrix exponential function. Existing acyclicity characterizations are based on the idea that powers of an adjacency matrix contain information about walks and cycles. In this work, we propose a new acyclicity characterization based on the log-determinant (log-det) function, which leverages the nilpotency property of DAGs. To deal with the inherent asymmetries of a DAG, we relate the domain of our log-det characterization to the set of $\textit{M-matrices}$, which is a key difference to the classical log-det function defined over the cone of positive definite matrices. Similar to acyclicity functions previously proposed, our characterization is also exact and differentiable. However, when compared to existing characterizations, our log-det function: (1) Is better at detecting large cycles; (2) Has better-behaved gradients; and (3) Its runtime is in practice about an order of magnitude faster. From the optimization side, we drop the typically used augmented Lagrangian scheme and propose DAGMA ($\textit{DAGs via M-matrices for Acyclicity}$), a method that resembles the central path for barrier methods. Each point in the central path of DAGMA is a solution to an unconstrained problem regularized by our log-det function, then we show that at the limit of the central path the solution is guaranteed to be a DAG. Finally, we provide extensive experiments for $\textit{linear}$ and $\textit{nonlinear}$ SEMs and show that our approach can reach large speed-ups and smaller structural Hamming distances against state-of-the-art methods. Code implementing the proposed method is open-source and publicly available at https://github.com/kevinsbello/dagma.
Aiming to address the currently low accuracy of domestic industrial defect detection, this paper proposes a Two-Stage Industrial Defect Detection Framework based on Improved-YOLOv5 and Optimized-Inception-ResnetV2, which completes positioning and classification tasks through two specific models. In order to make the first-stage recognition more effective at locating insignificant small defects with high similarity on the steel surface, we improve YOLOv5 from the backbone network, the feature scales of the feature fusion layer, and the multiscale detection layer. In order to enable second-stage recognition to better extract defect features and achieve accurate classification, we embed the convolutional block attention module (CBAM) attention mechanism module into the Inception-ResnetV2 model, then optimize the network architecture and loss function of the accurate model. Based on the Pascal Visual Object Classes 2007 (VOC2007) dataset, the public dataset NEU-DET, and the optimized dataset Enriched-NEU-DET, we conducted multiple sets of comparative experiments on the Improved-YOLOv5 and Inception-ResnetV2. The testing results show that the improvement is obvious. In order to verify the superiority and adaptability of the two-stage framework, we first test based on the Enriched-NEU-DET dataset, and further use AUBO-i5 robot, Intel RealSense D435 camera, and other industrial steel equipment to build actual industrial scenes. In experiments, a two-stage framework achieves the best performance of 83.3% mean average precision (mAP), evaluated on the Enriched-NEU-DET dataset, and 91.0% on our built industrial defect environment.
Abdur Rasool, Chayut Bunterngchit, Tiejian Luo
et al.
Breast cancer death rates are higher than any other cancer in American women. Machine learning-based predictive models promise earlier detection techniques for breast cancer diagnosis. However, making an evaluation for models that efficiently diagnose cancer is still challenging. In this work, we proposed data exploratory techniques (DET) and developed four different predictive models to improve breast cancer diagnostic accuracy. Prior to models, four-layered essential DET, e.g., feature distribution, correlation, elimination, and hyperparameter optimization, were deep-dived to identify the robust feature classification into malignant and benign classes. These proposed techniques and classifiers were implemented on the Wisconsin Diagnostic Breast Cancer (WDBC) and Breast Cancer Coimbra Dataset (BCCD) datasets. Standard performance metrics, including confusion matrices and K-fold cross-validation techniques, were applied to assess each classifier’s efficiency and training time. The models’ diagnostic capability improved with our DET, i.e., polynomial SVM gained 99.3%, LR with 98.06%, KNN acquired 97.35%, and EC achieved 97.61% accuracy with the WDBC dataset. We also compared our significant results with previous studies in terms of accuracy. The implementation procedure and findings can guide physicians to adopt an effective model for a practical understanding and prognosis of breast cancer tumors.
Denne rapporten er en sammenstilling av det eksisterende kunnskapsgrunnlaget når det gjelder sjøsamenes rettigheter til fiske i det tradisjonelle samiske bosettingsområdet. Rapporten gir et omriss av historien til sjøsamene, slik denne er dokumentert gjennom flere tidligere utredninger, særlig Kystfiskeutvalgets utredning (NOU 2008: 5 Retten til fiske i havet utenfor Finnmark) og Sannhets- og forsoningskommisjonens rapport til Stortinget (Dokument 19 (2022–2023) Sannhet og forsoning – grunnlag for et oppgjør med fornorskingspolitikk og urett mot samer, kvener/norskfinner og skogfinner). Det er særlig to statlige tiltak som har rammet sjøsamene negativt: statens fornorskningspolitikk som startet i andre halvdel av 1800-tallet og innføringen av fartøykvoter i 1989. Ved førstnevnte ble sjøsamene i stor grad fratatt sitt språk. Ved sistnevnte ble de i stor grad fratatt sin tradisjonelle levevei. Rapporten analyserer for det første relevante folkerettslige kilder, hvoretter Norge er forpliktet til å sikre grunnlaget for denne delen av samisk kultur. Et sentralt funn er at, selv om eksisterende generelle menneskerettsinstrumenter og urfolksspesifikke instrumenter ikke fastsetter uttrykkelige bestemmelser som anerkjenner urfolks rettigheter til tradisjonelt brukte marine områder og tilhørende ressurser, disse instrumenter kan tolkes og anvendes på en måte som anerkjenner samenes rettigheter til marine områder og ressurser. På samme måte, fraværet av uttrykkelige referanser til urfolk i UNCLOS ikke innebærer at konvensjonen begrenser eller utelukker urfolks rettigheter. Snarere viser vi at internasjonale menneskerettigheter som gjelder urfolk, kan påvirke tolkningen av de eksisterende reglene og prinsippene i havretten. For det andre analyserer rapporten den rettslige oppfølgingen av Kystfiskeutvalgets forslag i lys av relevante menneskerettigheter. I denne sammenhengen er Fosen-saken fra 2021 av betydning, og rapporten diskuterer hvorvidt Høyesteretts argumentasjon for at det forelå brudd på menneskerettighetene til reindriftsutøverne på Fosen, har overføringsverdi til sjøsamenes rettsstilling i dag.
We introduce MQ-Det, an efficient architecture and pre-training strategy design to utilize both textual description with open-set generalization and visual exemplars with rich description granularity as category queries, namely, Multi-modal Queried object Detection, for real-world detection with both open-vocabulary categories and various granularity. MQ-Det incorporates vision queries into existing well-established language-queried-only detectors. A plug-and-play gated class-scalable perceiver module upon the frozen detector is proposed to augment category text with class-wise visual information. To address the learning inertia problem brought by the frozen detector, a vision conditioned masked language prediction strategy is proposed. MQ-Det's simple yet effective architecture and training strategy design is compatible with most language-queried object detectors, thus yielding versatile applications. Experimental results demonstrate that multi-modal queries largely boost open-world detection. For instance, MQ-Det significantly improves the state-of-the-art open-set detector GLIP by +7.8% AP on the LVIS benchmark via multi-modal queries without any downstream finetuning, and averagely +6.3% AP on 13 few-shot downstream tasks, with merely additional 3% modulating time required by GLIP. Code is available at https://github.com/YifanXu74/MQ-Det.
Samuel Karumba, Subbu Sethuvenkatraman, Volkan Dedeoglu
et al.
ABSTRACT The increasing adoption of clean energy technologies, including solar and wind generation, demand response, energy efficiency, and energy storage (e.g. batteries and electric vehicles) have led to the evolution of the traditional electricity markets from centralised energy trading systems into Distributed Energy Trading (DET) systems. Consequently, savvy business executives are exploring how blockchain might impact their competitive advantage in the emerging DET markets. Due to its salient features of distributed ledger, consensus mechanisms, cryptography, and smart contracts, blockchain technology is being used to provide decentralised trust, immutability, security and privacy, and transparency in DET system. However, integrating blockchain in DET systems is facing technical, administrative, standardisation and economic barriers. Consequently, we seek to conduct a comprehensive market analysis to identify the specific challenges hindering the integration of blockchain in DET systems. Nonetheless, we noticed that there isn't any evaluation and review framework for conducting a systematic literature review on blockchain-based DET systems. Therefore, in this work we first proposed a conceptual evaluation and review framework for conducting a systematic literature review on blockchain-based DET systems. Then, using the proposed framework, we reviewed the current studies on blockchain-based DET systems to the identify specific challenges hindering the adoption of blockchain and their proposed solutions. Our review found that, although there has been tremendous progress in addressing the technical barriers, the administrative, standardisation and economic barriers have grossly been under reviewed.
In this paper, we describe the algorithm to measure the stroke and the temperature of solenoid using PWM driving current at two points based on the electric characteristics of the solenoid with CNN, without mechanical attachments. We describe the evaluation experimental results of the stroke and the temperature prediction. We also describe the preliminary experimental results of controlling the solenoid stroke at intermediate position.
In the modern graphics processing unit (GPU)/artificial intelligence (AI) era, flip-flop (FF) has become one of the most power-hungry blocks in processors. To address this issue, a novel single-phase-clock dual-edge-triggering (DET) FF using a single-transistor-clocked (STC) buffer (STCB) is proposed. The STCB uses a single-clocked transistor in the data sampling path, which completely removes clock redundant transitions (RTs) and internal RTs that exist in other DET designs. Verified by post-layout simulations in 22 nm fully depleted silicon on insulator (FD-SOI) CMOS, when operating at 10% switching activity, the proposed STC-DET outperforms prior state-of-the-art low-power DET in power consumption by 14% and 9.5%, at 0.4 and 0.8 V, respectively. It also achieves the lowest power-delay-product (PDP) among the DETs.
Metal surface defect detection has been a challenge in the industrial field. The current metal surface defect algorithms target only at a few types of defects and fail to perform well on defects with different scales. In this paper, a large number of metal surface defects are studied based on GC10-DET data set. An improved yolov5 detection network is designed targeting defects of various scales, especially of small-scaled objects, using a specific data enhancement method to regularize and an effective loss function to address data imbalance caused by small-scaled object defects. Finally, the comparative experiment on GC10-DET data set proves the major improvements on accuracy superiority of the proposed method.
Flux as well as spatial and angular resolution for a microbeam small-angle x-ray scattering set-up comprising Laue optics and multiple focusing elements are modeled within five-dimensional phase space analysis. A variety of x-ray optics configurations for highest angular resolution and for highest spatial resolution are analyzed.
The ALICE Time-Of-Flight (TOF) detector at LHC is based on the Multigap Resistive Plate Chambers (MRPCs). The TOF performance during LHC Run 2 is here reported. Particular attention is given to the improved time resolution reached by TOF detector of $56$ ps, with the consequently improved particle identification capabilities.