[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4221":3,"related-4221":62},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":18,"tags":20,"primary_topic":9,"secondary_topics":21,"classification":22,"search_phrases":41,"slug":42,"view_count":15,"doi":43,"paper":44,"created_at":61},4221,"Improving Image Classification Performance with Modern Data Augmentation and Vision Transformer","https:\u002F\u002Fdoi.org\u002F10.48084\u002Fetasr.20583","Visual cognition, one of the main tasks of computer vision, has many applications, including object detection, face recognition, and self-driving automobiles. This paper discusses deep learning applications to visual cognition, including a brief history, some of its applications, and some architectures, such as Residual Networks and Residual-Inception. Visual cognition faces significant challenges when dealing with objects that have comparable forms but represent different classes. The proposed architecture in this paper incorporates Modern Data Augmentation and Vision Transformers (MDAViT) to improve accuracy. The model is trained and evaluated on the CIFAR-10 dataset, demonstrating higher accuracy against existing self-supervised methods.","视觉认知是计算机视觉的主要任务之一，具有许多应用，包括目标检测、人脸识别和自动驾驶汽车。本文讨论了深度学习在视觉认知中的应用，包括简要历史、一些应用以及一些架构，如残差网络（Residual Networks）和残差初始网络（Residual-Inception）。视觉认知在处理具有相似形态但代表不同类别的对象时面临重大挑战。本文提出的架构结合了现代数据增强和视觉Transformer（MDAViT）以提高准确率。该模型在CIFAR-10数据集上进行训练和评估，相较于现有的自监督方法展现出更高的准确率。",null,"Engineering Technology & Applied Science Research","2026-10-02T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"该论文聚焦通用计算机视觉的图像分类方法（MDAViT、CIFAR-10），与三农、农业信息化、智慧农业等主题无直接关联，不建议进入每日精选。",[19],{"name":10,"url":6},[12],[],{"status":23,"locked":14,"version":24,"method":25,"evidence":26},"needs_review","2026-10-22.2","rules",{"candidates":27,"agricultural_evidence":14,"reason":40},[28],{"code":29,"score":30,"supported":31,"title":32,"abstract":33,"tags":39},"I2",9,true,[],[34,35,36,37,38],"目标检测","深度学习","计算机视觉","deep learning","computer vision",[],"农业相关性需要复核",[],"ImprovingImageClassificationPerformancew-4221","10.48084\u002Fetasr.20583",{"doi":43,"openalex_id":45,"authors":46,"venue":10,"cited_by_count":15,"oa_url":52,"card":53,"direction":59,"ingested_from":60},"W7219007446",[47,49],{"name":48,"orcid":9},"Abderrahmane Bouidi",{"name":50,"orcid":51},"Lahcen Oughdir","https:\u002F\u002Forcid.org\u002F0000-0003-0151-863X","https:\u002F\u002Fwww.etasr.com\u002Findex.php\u002FETASR\u002Farticle\u002Fdownload\u002F20583\u002F7239",{"tldr":54,"method":55,"finding":56,"direction":57,"opportunity":58},"提出MDAViT模型，结合现代数据增强与视觉Transformer提升图像分类精度。","现代数据增强与Vision Transformer，在CIFAR-10数据集上训","MDAViT在CIFAR-10上准确率高于现有自监督方法。","农业人工智能与决策模型","可将MDAViT迁移至农业图像分类（如病虫害识别），探索农业场景下的数据增强策略。","智慧农业 \u002F 农业物联网","openalex","2026-10-05T23:30:13.198400Z",{"total":15,"page":63,"page_size":63,"items":64},1,[]]