• 
    

    
    

      99热精品在线国产_美女午夜性视频免费_国产精品国产高清国产av_av欧美777_自拍偷自拍亚洲精品老妇_亚洲熟女精品中文字幕_www日本黄色视频网_国产精品野战在线观看

      ?

      基于負邊距損失的小樣本目標檢測

      2022-11-30 08:39:32杜蕓彥李鴻楊錦輝江彧毛耀
      計算機應用 2022年11期
      關鍵詞:類別損失樣本

      杜蕓彥,李鴻,楊錦輝,江彧,毛耀*

      基于負邊距損失的小樣本目標檢測

      杜蕓彥1,2,李鴻1,2,楊錦輝1,2,江彧1,2,毛耀1,2*

      (1.中國科學院大學,北京 100049; 2.中國科學院光束控制重點實驗室(中國科學院光電技術研究所),成都 610207)(?通信作者電子郵箱maoyao@ioe.ac.cn)

      現(xiàn)有的大部分目標檢測算法都依賴于大規(guī)模的標注數(shù)據(jù)集來保證檢測的正確率,但某些場景往往很難獲得大量標注數(shù)據(jù),且耗費大量人力、物力。針對這一問題,提出了基于負邊距損失的小樣本目標檢測方法(NM?FSTD),將小樣本學習(FSL)中屬于度量學習的負邊距損失方法引入目標檢測,負邊距損失可以避免將同一新類的樣本錯誤地映射到多個峰值或簇,有助于小樣本目標檢測中新類的分類。首先采用大量訓練樣本和基于負邊距損失的目標檢測框架訓練得到具有良好泛化性能的模型,之后通過少量具有標簽的目標類別的樣本對模型進行微調,并采用微調后的模型對目標類別的新樣本進行目標檢測。為了驗證NM?FSTD的檢測效果,使用MS COCO進行訓練和評估。實驗結果表明,所提方法AP50達到了22.8%,與Meta R?CNN和MPSR相比,準確率分別提高了3.7和4.9個百分點。NM?FSTD能有效提高在小樣本情況下對目標類別的檢測性能,解決目前目標檢測領域中數(shù)據(jù)不足的問題。

      目標檢測;小樣本學習;負邊距損失;度量學習

      0 引言

      近年來,為了解決目標檢測中數(shù)據(jù)量不足的問題,越來越多的研究人員嘗試將FSL與目標檢測方法相結合。通過對數(shù)據(jù)、訓練策略、模型結構以及損失函數(shù)等部分的巧妙設計,使模型僅采用少量標注樣本就可以快速學習到具有一定泛化性能的檢測模型?,F(xiàn)有的大部分小樣本目標檢測方法主要可分成三類:基于微調的方法、基于度量學習的方法以及基于模型結構的方法[31]。

      基于微調的方法是采用大量標注數(shù)據(jù)訓練得到預訓練模型,并用該模型參數(shù)初始化目標域模型,最后再根據(jù)新類的少量標注樣本進行微調。在文獻[32]中,小樣本遷移檢測器(Low?Shot Transfer Detector, LSTD)模型利用SSD設計邊界框回歸,利用Faster R?CNN設計目標分類;同時提出了基于源域和目標域的轉移指數(shù)(Transfer?Knowledge, TK)以及背景抑制(Background?Depression, BD)的正則化方法。TK主要在目標提案中遷移標簽知識,BD主要是用邊界框來做特征圖的額外監(jiān)督,以此來抑制背景的干擾。在文獻[33]中,首先使用目標檢測網絡對前景區(qū)域進行提取,然后借助紋理特征等訓練更為準確的分類器,同時采用文獻[32]中的正則化方法去提高模型的泛化性能。

      一些研究人員將屬于度量學習的FSL方法引入目標檢測領域也取得了良好的效果。在文獻[34]中引入了貝葉斯條件概率理論,提出了單樣本條件目標檢測(One?Shot Conditional object Detection, OSCD)框架。首先采用孿生網絡進行特征采樣,然后將兩個特征融合輸入條件區(qū)域候選網絡(Conditional?Region Proposal Network, C?RPN)中計算感興趣區(qū)域(Region of Interest, ROI)相似度和邊界框,再把相似的區(qū)域用在條件分類器(Conditional?Classifier, C?Classifier)進行相似度計算和邊界框計算。文獻[35]中提出了一種新的距離度量學習(Distance Metric Learning, DML)方法,在一個端到端的訓練過程中,同時學習主干網絡參數(shù)、嵌入空間以及該空間中每個訓練類別的多模態(tài)分布,并將提出的DML架構作為分類頭合并到一個標準的目標檢測模型中實現(xiàn)對小樣本的目標檢測。文獻[36]中提出了對比提議編碼(Contrastive Proposal Encoding)進行小樣本目標檢測,利用對比提議編碼損失使同簇更緊密、不同簇之間距離增大,提高了檢測模型在小樣本設置中的通用性。

      基于模型結構方法是通過重新設計模型結構實現(xiàn)小樣本目標檢測。文獻[37]中提出了元學習小樣本檢測(Few?Shot Detection, FSD)框架,該框架包含一個元學習器和一個目標檢測器。元學習系統(tǒng)從一系列的FSD任務中學習一個元學習器,可以指導檢測器如何在一個新的小樣本任務中快速準確地更新網絡。文獻[38]中提出了一個基于Faster R?CNN的小樣本目標檢測(Few?Shot Object Detection, FSOD)模型,該模型在區(qū)域候選網絡(Region Proposal Network, RPN)中加入了注意力機制,并使用多關系檢測器作為分類器,同時提出了一種對比訓練策略,使檢測器擁有判斷相同類和區(qū)分不同類的能力。

      1 FSOD模型

      FSOD模型的總體框架[38]以Faster R?CNN為基礎。在此基礎上,加入了注意力區(qū)域候選網絡(Attention?RPN)和多關系檢測器(Multi?Relation Detector),圖1為FSOD的總體結構。

      多關系檢測器通過計算支持圖像特征和查詢圖像特征的相似性,留下相似性高的區(qū)域,剔除相似性低的區(qū)域,以此得到更準確的候選區(qū)域。其中包含三個關系,分別為:全局關系、局部關系和模塊關系。全局關系使用全局表示來匹配圖像;局部關系獲取像素到像素的匹配關系;模塊關系模擬一對多像素關系。通過這三種關系并行計算相似度,將得到的結果相加取平均就獲得了該候選區(qū)域最終的置信度,留下置信度閾值之上的框從而得到最終的預測結果。

      圖1 FSOD模型的總體結構

      2 負邊距損失的小樣本目標檢測

      2.1 負邊距損失函數(shù)

      在目標檢測分類任務中,通常會采用Softmax分類器直接輸出樣本屬于每個類的概率,以此對目標進行分類。常規(guī)Softmax損失函數(shù)如式(1)所示:

      2.2 負邊距小樣本檢測框架

      本節(jié)將在上述目標檢測框架中采用負邊距損失,構建一個小樣本目標檢測框架NM?FSTD。如圖2所示,負邊距損失主要作用于NM?FSTD的目標分類部分,應用于Softmax分類器。

      圖2 NM?FSTD總體框架

      圖3 負邊距Softmax損失與負邊距余弦Softmax損失的計算過程

      3 實驗與結果分析

      3.1 數(shù)據(jù)集

      本文實驗使用MS COCO[45]中的60個類別作為訓練類,并使用剩下的與PASCAL VOC中包含的20個類別相同的類別作為新的評估類別。MS COCO數(shù)據(jù)集是一個大型的、豐富的數(shù)據(jù)集,常用于目標檢測與實例分割、人體關鍵點檢測等。該數(shù)據(jù)集包括81類目標,328 000幅圖像和2 500 000個標簽。PASCAL VOC數(shù)據(jù)集是用于圖像分類和目標檢測兩個任務的基準測試集,主要分為VOC 2007和VOC 2012,每部分包含20個常見類別,主要包括貓狗等動物、飛機自行車等交通工具、家具等。其中:VOC 2007包含5 011幅訓練和驗證圖像,4 952幅測試圖像;VOC 2012包含11 540幅訓練和驗證圖像,10 991幅測試圖像。

      3.2 模型訓練和評價指標

      此外,本文也設計了實驗用于驗證負邊距損失函數(shù)有利于在小樣本情況下對新類別樣本進行目標分類,從而有利于新類別的小樣本目標檢測。本文選取miniImagenet數(shù)據(jù)集用于驗證,其中的64個類別作為基礎類別,16個類別作為驗證類別,20個類別作為新類別,分別用于訓練、驗證和測試,輸入圖像大小為224×224,圖像批量大小為256。

      3.3 結果分析

      表1 miniImagenet數(shù)據(jù)集在不同下采用余弦Softmax損失的分類準確率對比 單位: %

      表2 miniImagenet數(shù)據(jù)集在不同下采用 Softmax損失的分類準確率對比 單位: %

      利用MS COCO數(shù)據(jù)集中的60個類別進行訓練,剩下的與PASCAL VOC數(shù)據(jù)集中的20個類別相同的類別進行評估,并且訓練集和評估集的類別不重合;對比本文方法(負邊距Softmax FSTD和負邊距余弦Softmax FSTD)與LSTD、FR(Feature Reweighting)[46]、Meta R?CNN[47]、MPSR(Multi?Scale Positive Sample Refinement)[50]、TFA(Two?stage Fine?tuning Approach)[49]、SRR?FSD(Semantic Relation Reasoning Few? Shot Object Detection)[48]、FSCE(Few?Shot object detection via Contrastive proposal Encoding)[36]、FSOD[38]、Cos?FSOD(指將FSOD的Softmax損失修改為余弦Softmax損失)等,結果如表3。可以看出本文方法的結果優(yōu)于現(xiàn)有的大部分小樣本目標檢測方法,提升了小樣本目標檢測性能。

      此外,表3也列出了各個方法的主干網絡、參數(shù)量及每秒浮點運算次數(shù)(FLoating-point OPerations per second, FLOPs),可以看出,在參數(shù)量與FLOPs上,本文方法也有一定的優(yōu)勢。

      表3各方法的性能對比

      Tab.3 Performance comparison of different methods

      表4 負邊距損失對小樣本目標檢測準確率的影響 單位: %

      此外,本文對骨干網絡也進行了消融實驗,結果如表5所示。在表5中,采用負邊距余弦Softmax小樣本目標檢測方法(Negative?Margin Cosine Softmax FSTD),其余實驗設置不變,選取了不同的骨干網絡進行實驗,得到了相應的檢測精度。實驗結果表明,選取ResNet?50作為骨干網絡比ResNet-34在AP/AP50/AP75上分別提高了2.8/3.3/3.0個百分點;而ResNet?101比ResNet?50在AP/AP50/AP75上分別提高了1.8/1.5/1.7個百分點,比ResNet?34在AP/AP50/AP75上分別提高了4.6/4.8/4.7個百分點。

      表5 骨干網絡的消融實驗結果 單位: %

      圖4顯示了對于訓練類別,圖像中的大部分對象利用NM?FSTD都能夠準確地定位到它們的位置并按概率對其進行分類,判斷出樣本所屬類別。圖5展示了在新類別上,即模型沒有采用大量數(shù)據(jù)學習過的類別,NM?FSTD的檢測效果,圖像左上角表示該幅圖像的支持樣本,可以看出對于圖像中的目標基本都能夠進行準確定位和正確分類。

      圖4 NM?FSTD在訓練類別上的檢測結果

      圖5 NM?FSTD在新類別上的檢測結果

      4 結語

      本文對小樣本目標檢測問題進行了分析和研究。首先,針對現(xiàn)在目標檢測中樣本數(shù)據(jù)不足的問題,總結和分析了現(xiàn)有的目標檢測、小樣本學習以及小樣本目標檢測方法,提出了將小樣本學習中的度量學習方法負邊距損失引入目標檢測框架FSOD中,并通過實驗對其有利于新類的學習和判別進行了驗證;然后,基于FSOD提出了引入負邊距損失的新的小樣本目標檢測框架NM?FSTD,其中負邊距損失作用于目標分類部分的Softmax分類器,使模型能進行端到端的訓練;最后,使用MS COCO數(shù)據(jù)集對提出的方法進行了驗證和評估,取得了較好的結果,說明了NM?FSTD的有效性。在未來的工作中,還需要更進一步地研究小樣本學習方法與目標檢測方法的結合,提出更具有普適性和可遷移性的小樣本目標檢測方法。

      [1] LIU W, ANGUELOY D, ERHAN D, et al. SSD: Single Shot MultiBox Detector[C]// Proceedings of the 2016 European Conference on Computer Vision, LNIP 9905. Cham: Springer, 2016: 21-37.

      [2] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real?time object detection[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 779-788.

      [3] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 6517-6525.

      [4] REDMON J, FARHADI A. YOLOv3: an incremental improvement [EB/OL]. [2021-08-10]. https://doi.org/10.48550/arXiv.1804.02767.

      [5] BOCHKOVSKIY A, WANG C Y, LIAO H. YOLOv4: optimal speed and accuracy of object detection [EB/OL]. [2021-07-05]. https://doi.org/10.48550/arXiv.2004.10934.

      [6] 劉丹,吳亞娟,羅南超,等. 嵌入注意力和特征交織模塊的Gaussian?YOLO v3目標檢測[J]. 計算機應用, 2020, 40(8): 2225-2230.(LIU D, WU Y J, LUO N C, et al. Object detection of Gaussian?YOLO v3 implanting attention and feature intertwine modules[J]. Journal of Computer Applications, 2020, 40(8): 2225-2230.)

      [7] HE K, ZHANG X, REN S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 37(9):1904-1916.

      [8] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]// Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 580-587.

      [9] GIRSHICK R. Fast RCNN[C]// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 1440-1448.

      [10] REN S, HE K, GIRSHICK R, et al. Faster R?CNN: towards real? time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.

      [11] WANG Y,YAO Q, KWOK J T, et al. Generalizing from a few examples: a survey on few?shot learning[J]. ACM Computing Surveys, 2020, 53(3):1-34.

      [12] MILLER E G, MATSAKIS N E, VIOLA P A. Learning from one example through shared densities on transforms[C]// Proceedings of the 2000 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2000: 464-471.

      [13] SCHWARTZ E, KARLINSKY L, SHTOK J, et al. Delta? encoder: an effective sample synthesis method for few?shot object recognition[C]// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2018: 2850-2860.

      [14] 甘嵐,沈鴻飛,王瑤,等. 基于改進DCGAN的數(shù)據(jù)增強方法[J]. 計算機應用, 2021, 41(5): 1305-1313.(GAN L, SHEN H F, WANG Y, et al. Data augmentation method based on improved deep convolutional generative adversarial networks[J]. Journal of Computer Applications, 2021, 41(5): 1305-1313.)

      [15] 陳佛計,朱楓,吳清瀟,等. 基于生成對抗網絡的紅外圖像數(shù)據(jù)增強[J]. 計算機應用, 2020, 40(7): 2084-2088.(CHEN F J, ZHU F, WU Q X, et al. Infrared image data augmentation based on generative adversarial network[J]. Journal of Computer Applications, 2020, 40(7): 2084-2088.)

      [16] HARIHARAN B, GIRSHICK R. Low?shot visual recognition by shrinking and hallucinating features[C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 3037-3046.

      [17] PFISTER T, CHARLES J, ZISSERMAN A. Domain?adaptive discriminative one?shot learning of gestures[C]// Proceedings of the 2014 European Conference on Computer Vision, LNCS 8694. Cham: Springer, 2014: 814-829.

      [18] DOUZE M, SZLAM A, HARIHARAN B, et al. Low?shot learning with large?scale diffusion[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2018: 3349-3358.

      [19] GRANT E, FINN C, LEVINE S, et al. Recasting gradient?based meta?learning as hierarchical Bayes [EB/OL]. [2021-08-10]. https://doi.org/10.48550/arXiv.1801.08930.

      [20] TSAI Y, SALAKHUTDINOV R. Improving one?shot learning through fusing side information [EB/OL]. [2021-06-19]. https://doi.org/10.48550/arXiv.1710.08347.

      [21] GAO H, SHOU Z, ZAREIAN A, et al. Low?shot learning via covariance?preserving adversarial augmentation networks[C]// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2018: 983-993.

      [22] VINYALS O, BLUNDELL C, LILLICRAP T, et al. Matching networks for one shot learning[C]// Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2016: 3637-3645.

      [23] SNELL J, SWERSKY K, ZEMEL R S. Prototypical networks for few?shot learning[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2017: 4077-4087.

      [24] SUNG F, YANG Y, ZHANG L, et al. Learning to compare: relation network for few?shot learning[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 1199-1208.

      [25] KOCH G R, ZEMEL R, SALAKHUTDINOV R. Siamese neural networks for one?shot image recognition[C/OL]// Proceedings of the 2015 32nd International Conference on Machine Learning. Brookline, MA: JMLR.org, 2015 [2021-06-05]. http://www.cs.cmu.edu/~rsalakhu/papers/oneshot1.pdf.

      [26] MUNKHDALAI T, YU H. Meta networks[C]// Proceedings of the 34th International Conference on Machine Learning. Brookline, MA: JMLR.org, 2017: 2554-2563.

      [27] LAKE B M, SALAKHUTDINOV R, TENENBAUM J B. Human? level concept learning through probabilistic program induction[J]. Science, 2015, 350(6266): 1332-1338.

      [28] KINGMA D P, WELLING M. Auto?encoding variational Bayes [EB/OL]. [2021-07-10]. https://doi.org/10.48550/arXiv. 1312.6114.

      [29] HOFFMAN J, TZENG E, DONAHUE J, et al. One?shot adaptation of supervised deep convolutional models [EB/OL]. [2021-06-15]. https://doi.org/10.48550/arXiv.1312.6204.

      [30] LEE Y, CHOI S. Gradient?based meta?learning with learned layerwise metric and subspace [EB/OL]. [2021-05-10]. https://doi.org/10.48550/arXiv.1801.05558.

      [31] 潘興甲,張旭龍,董未名,等.小樣本目標檢測的研究現(xiàn)狀[J].南京信息工程大學學報(自然科學版),2019,11(6):698-705.(PAN X J, ZHANG X L, DONG W M, et al. A survey of few?shot object detection[J]. Journal of Nanjing University of Information Science and Technology (Natural Science Edition), 2019,11(6):698-705)

      [32] CHEN H, WANG Y, WANG G, et al. LSTD: a low?shot transfer detector for object detection [EB/OL]. [2021-04-25]. https://doi.org/10.48550/arXiv.1803.01529.

      [33] SINGH P, VARADARAJAN S, SINGH A N, et al. Multidomain document layout understanding using few shot object detection [EB/OL]. [2021-05-10]. https://doi.org/10.48550/arXiv.1808.07330.

      [34] ZHANG T, ZHANG Y, SUN X, et al. Comparison network for one?shot conditional object detection [EB/OL]. [2021-08-10]. https://doi.org/10.48550/arXiv.1904.02317.

      [35] KARLINSKY L, SHTOK J, HARARY S, et al. RepMet: representative?based metric learning for classification and few?shot object detection[C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington, DC: IEEE Computer Society, 2019: 5192-5201.

      [36] SUN B, LI B, CAI S, et al. FSCE: Few?shot object detection via contrastive proposal encoding[C]// Proceedings of the 2021 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2021: 7352-7362.

      [37] FU K, ZHANG T, ZHANG Y, et al. Meta?SSD: towards fast adaptation for few?shot object detection with meta?learning[J]. IEEE Access, 2019, 7: 77597-77606.

      [38] FAN Q, ZHUO W, TANG C K, et al. Few?shot object detection with attention?RPN and multi?relation detector[C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2020:4012-4021.

      [39] WEN Y, ZHANG K, LI Z, et al. A discriminative feature learning approach for deep face recognition[C]// Proceedings of the 2016 European Conference on Computer Vision, LNIP 9911. Cham: Springer, 2016: 499-512.

      [40] LIU W, WEN Y, YU Z, et al. Large?margin Softmax loss for convolutional neural networks [EB/OL]. [2021-07-01]. https://doi.org/10.48550/arXiv.1612.02295.

      [41] DENG J, GUO J, ZAFEIRIOU S. ArcFace: additive angular margin loss for deep face recognition [EB/OL]. [2021-05-17]. https://doi.org/10.48550/arXiv.1801.07698.

      [42] WANG H, WANG Y, ZHOU Z, et al. CosFace: large margin cosine loss for deep face recognition[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2018: 5265-5274.

      [43] LIU B, CAO Y, LIN Y, et al. Negative margin matters: understanding margin in few?shot classification [C]// Proceedings of the 2020 European Conference on Computer Vision, LNIP 12361. Cham: Springer, 2020: 438-455.

      [44] LIU W, WEN Y, YU Z, et al. SphereFace: deep hypersphere embedding for face recognition[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2017: 6738-6746.

      [45] LIN T Y, MAIRE M, BELONGIE S,et al. Microsoft COCO: common objects in context[C]// Proceedings of the 2014 European Conference on Computer Vision, LNIP 8693. Cham: Springer, 2014: 740-755.

      [46] KANG B, ZHUANG L, XIN W, et al. Few?shot object detection via feature reweighting[C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 8420-8429.

      [47] YAN X, CHEN Z, XU A, et al. Meta R?CNN: towards general solver for instance?level low?shot learning[C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 9576-9585.

      [48] ZHU C, CHEN F, AHMED U, et al. Semantic relation reasoning for shot?stable few?shot object detection [EB/OL]. [2021-08-05]. https://doi.org/10.48550/arXiv.2103.01903.

      [49] WANG X, HUANG T E, DARRELL T, et al. Frustratingly simple few-shot object detection [EB/OL]. [2021-08-10]. https://doi.org/10.48550/arXiv.2003.06957.

      [50] WU J, LIU S, HUANG D, et al. Multi?scale positive sample refinement for few?shot object detection [C]// Proceedings of the 2020 European Conference on Computer Vision, LNIP 12361. Cham: Springer, 2020: 456-472.

      Few?shot target detection based on negative?margin loss

      DU Yunyan1,2, LI Hong1,2, YANG Jinhui1,2, JIANG Yu1,2, MAO Yao1,2*

      (1,100049,;2,(),610207,)

      Most of the existing target detection algorithms rely on large?scale annotation datasets to ensure the accuracy of detection, however, it is difficult for some scenes to obtain a large number of annotation data and it consums a lot of human and material resources. In order to resolve this problem, a Few?Shot Target Detection method based on Negative Margin loss (NM?FSTD) was proposed. The negative margin loss method belonging to metric learning in Few?Shot Learning (FSL) was introduced into target detection, which could avoid mistakenly mapping the samples of the same novel classes to multiple peaks or clusters and helping to the classification of novel classes in few?shot target detection. Firstly, a large number of training samples and the target detection framework based on negative margin loss were used to train the model with good generalization performance. Then, the model was finetuned through a small number of labeled target category samples. Finally, the finetuned model was used to detect the new sample of target category. To verify the detection effect of NM?FSTD, MS COCO was used for training and evaluation. Experimental results show that the AP50of NM?FSTD reaches 22.8%; compared with Meta R?CNN (Meta Regions with CNN features) and MPSR (Multi?Scale Positive Sample Refinement), the accuracies are improved by 3.7 and 4.9 percentage points, respectively. NM?FSTD can effectively improve the detection performance of target categories in the case of few?shot, and solve the problem of insufficient data in the field of target detection.

      target detection; Few?Shot Learning (FSL); negative?margin loss; metric learning

      This work is partially supported by The National Key Research and Development Program of China (2017YFB1103002).

      DU Yunyan, born in 1997, M. S. candidate. Her research interests include target detection, few-shot learning.

      LI Hong, born in 1996, M. S. candidate. His research interests include deep learning, lightweight target detection.

      YANG Jinhui, born in 1996, M. S. candidate. His research interests include lightweight target detection.

      JIANG Yu, born in 1977, M. S., associate researcher. Her research interests include computer application technology, human computer interaction system.

      MAO Yao, born in 1978, Ph. D., researcher. His research interests include computer technology, machine vision, reinforcement learning.

      TP391.41

      A

      1001-9081(2022)11-3617-08

      10.11772/j.issn.1001-9081.2021091683

      2021?09?27;

      2022?05?25;

      2022?05?26。

      國家重點研發(fā)計劃項目(2017YFB1103002)。

      杜蕓彥(1997—),女,四川成都人,碩士研究生,主要研究方向:目標檢測、小樣本學習;李鴻(1996—),男,貴州畢節(jié)人,碩士研究生,主要研究方向:深度學習、輕量化目標檢測;楊錦輝(1996—),男,甘肅平涼人,碩士研究生,主要研究方向:輕量化目標檢測;江彧(1977—),女,安徽黃山人,副研究員,碩士,主要研究方向:人機交互系統(tǒng);毛耀(1978—),男,四川眉山人,研究員,博士,CCF會員,主要研究方向:機器視覺、強化學習。

      猜你喜歡
      類別損失樣本
      少問一句,損失千金
      胖胖損失了多少元
      用樣本估計總體復習點撥
      玉米抽穗前倒伏怎么辦?怎么減少損失?
      推動醫(yī)改的“直銷樣本”
      隨機微分方程的樣本Lyapunov二次型估計
      村企共贏的樣本
      服務類別
      新校長(2016年8期)2016-01-10 06:43:59
      一般自由碰撞的最大動能損失
      論類別股東會
      商事法論集(2014年1期)2014-06-27 01:20:42
      舒城县| 当雄县| 依兰县| 连平县| 潜江市| 美姑县| 富蕴县| 临高县| 高淳县| 那曲县| 洪洞县| 高密市| 富宁县| 阿坝| 巩留县| 重庆市| 五指山市| 昌乐县| 亚东县| 西乌珠穆沁旗| 鲁甸县| 凤台县| 长葛市| 金山区| 阳山县| 佛冈县| 阳高县| 龙陵县| 饶平县| 安多县| 虎林市| 剑阁县| 铁力市| 徐闻县| 嘉鱼县| 无为县| 嫩江县| 无极县| 深泽县| 屏东县| 钦州市|