[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2420":3},{"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,"view_count":15,"doi":22,"paper":23,"created_at":41},2420,"Face Aging Using Various Cycle GAN Models: A Comparative Analysis of Efficient Net Mobile Net and Standard Architectures","https:\u002F\u002Fdoi.org\u002F10.38094\u002Fjastt721117","Human face aging is a fundamental problem in computer vision and biometric analysis, with significant applications spanning forensic identification, entertainment and clinical assessment. Standard ResNet-based generators often exhibit mode collapse and insufficient preservation of identity-discriminative features. Moreover, training stability across a large number of epochs presents difficulties, particularly when balancing adversarial loss, cycle-consistency loss, and identity loss simultaneously. This research proposes and evaluates three distinct CycleGAN architectures for face aging such as CycleGAN-EfficientNetB1, CycleGAN MobileNetV2, and CycleGAN. All three models are trained on a dataset of cropped young and old facial images using the Adam optimizer with learning rate 0.0001 and identical loss weightings. Each model employs a shared adversarial training strategy combining MSE-based GAN loss, L1-based cycle-consistency loss with weight lambda=10, and L1-based identity loss with weight lambda=5. The EfficientNetB1 model uses frozen early encoder layers (first 3 feature blocks) producing 24-channel feature maps, while the MobileNetV2 model leverages the first 7 inverted bottleneck blocks producing 32-channel feature maps. The standard model uses a conventional conv-down-sample-resblock-upsample architecture with 9 residual blocks. Training over 200, 152, and 270 epochs respectively, the models achieved final generator losses of 3.69, 1.71, and 1.56. The experimental findings confirm that architectural choice of backbone significantly influences face aging quality in CycleGAN frameworks. The normal CycleGAN achieves the lowest final loss across all metrics, while MobileNet offers computational efficiency with competitive quality. This study establishes a comparative benchmark for CycleGAN-based face aging research.","人脸老化是计算机视觉和生物特征分析中的一个基础性问题，在法医鉴定、娱乐和临床评估等领域具有重要应用。标准的基于ResNet的生成器往往会出现模式崩溃以及身份判别特征保留不足的问题。此外，在大量训练轮次中保持训练稳定性也存在困难，尤其是在同时平衡对抗损失、循环一致性损失和身份损失时。本研究提出并评估了三种用于人脸老化的不同CycleGAN架构，即CycleGAN-EfficientNetB1、CycleGAN MobileNetV2和CycleGAN。三种模型均在由裁剪后的年轻和年老面部图像组成的数据集上进行训练，使用Adam优化器，学习率为0.0001，并采用相同的损失权重。每个模型都采用共享的对抗训练策略，结合基于MSE的GAN损失、权重lambda=10的基于L1的循环一致性损失，以及权重lambda=5的基于L1的身份损失。EfficientNetB1模型使用冻结的早期编码器层（前3个特征块），产生24通道特征图；而MobileNetV2模型利用前7个倒残差瓶颈块，产生32通道特征图。标准模型采用传统的卷积-下采样-残差块-上采样架构，包含9个残差块。分别训练200、152和270个轮次后，这些模型的最终生成器损失分别为3.69、1.71和1.56。实验结果证实，主干网络的架构选择会显著影响CycleGAN框架中的人脸老化质量。普通CycleGAN在所有指标上取得了最低的最终损失，而MobileNet则在具有竞争力的质量下提供了计算效率。本研究为基于CycleGAN的人脸老化研究建立了一个比较基准。",null,"Journal of Applied Science and Technology Trends","2026-09-12T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"人脸老化生成属通用计算机视觉研究，与三农、农业信息化、智慧农业无直接关联，不建议进入每日精选。",[19],{"name":10,"url":6},[21],"农业人工智能","10.38094\u002Fjastt721117",{"doi":22,"openalex_id":24,"authors":25,"venue":10,"cited_by_count":15,"oa_url":32,"card":33,"direction":39,"ingested_from":40},"W7212382506",[26,28,30],{"name":27,"orcid":9},"Tejaswini Sachin Deshmukh",{"name":29,"orcid":9},"Mahadeo Digambar Kokate",{"name":31,"orcid":9},"Dnyaneshwar Dadaji Ahire","https:\u002F\u002Fjastt.org\u002Findex.php\u002Fjasttpath\u002Farticle\u002Fdownload\u002F1117\u002F167",{"tldr":34,"method":35,"finding":36,"direction":37,"opportunity":38},"比较三种CycleGAN架构（EfficientNetB1、MobileNetV2、标准ResNet","CycleGAN结合MSE对抗损失、L1循环一致损失与身份损失，在年轻\u002F老年裁剪","标准CycleGAN最终损失最低，MobileNetV2计算高效且质量有竞争力，骨干网络选择显著影响","其他","可探索轻量级骨干与身份保持损失结合，并迁移至农业场景中的人脸\u002F个体识别与老化鲁棒性研究。","农业遥感与作物表型","openalex","2026-09-14T23:30:18.317511Z"]