본문 바로가기
KERD
논문KCI 등재

Spatially Weighted Convolutional Feature Aggregation for Image Retrieval

강상길|Enkhbayar Erdenee
한국엔터프라이즈아키텍처학회 (Korea Institute of Enterprise Architecture)|2017.09|정보화연구 (The Journal of Information Technology and Architecture)|제14권 제3호|pp. 221-229

0

조회

0

다운로드

0

인용

0

참고문헌

키워드

image retrievalconvolutional neural networkdeep convolutional featurefeature aggregation
주제분류과학기술학

초록

In this paper, we introduce a simple but efficient method to construct powerful imagerepresentation via spatially weighted deep convolutional feature aggregation for image retrieval. First,the convolutional features are extracted from the convolutional layer of the CNNs and proposed spatialweights are applied to the convolutional features. A sum pooling is performed to aggregate the spatiallyweighted convolutional features into the global image representation. We carry out extensiveexperiments on Oxford and Paris Building datasets and experiment results show that the proposedmethod achieves competitive performance compared to current state-of-the-art methods.

Abstract

In this paper, we introduce a simple but efficient method to construct powerful imagerepresentation via spatially weighted deep convolutional feature aggregation for image retrieval. First,the convolutional features are extracted from the convolutional layer of the CNNs and proposed spatialweights are applied to the convolutional features. A sum pooling is performed to aggregate the spatiallyweighted convolutional features into the global image representation. We carry out extensiveexperiments on Oxford and Paris Building datasets and experiment results show that the proposedmethod achieves competitive performance compared to current state-of-the-art methods.

참고문헌 (44)

  1. D. G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints", Int. J. Comput. Vis (2004)
  2. H. Jégou, "Aggregating local descriptors into a compact image representation", ~
  3. F. Perronnin, "Large-Scale Image Retrieval with Compressed Fisher Vectors", ~
  4. F. Radenovi, "Multiple Measurements and Joint Dimensionality Reduction for Large Scale Image Search with Short Vectors", ~
  5. Arandjelovi, "All about VLAD", ~
  6. G. Tolias, "Orientation covariant aggregation of local descriptors with embeddings", ~
  7. A. Babenko, "Neural Codes for Image Retrieval", ~
  8. A. S. Razavian, "Paper Visual Instance Retrieval with Deep Convolutional Networks", ~
  9. A. Krizhevsky, "ImageNet Classification with Deep Convolutional Neural Networks", Adv. Neural Inf. Process. Syst, pp.1~9 (2012)
  10. Y. LeCun, "Handwritten Digit Recognition with a Back-Propagation Network", 396~404 (1990)
  11. M. Oquab, "Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks", 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp.1717~1724 (2014)
  12. K. Chatfield, "Return of the Devil in the Details: Delving Deep into Convolutional Nets" (2014)
  13. A. S. Razavian, "CNN Features off-the-shelf: an Astounding Baseline for Recognition", ~
  14. R. Girshick, "Rich feature hierarchies for accurate object detection and semantic segmentation", Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit, pp.580~587 (2014)
  15. M. Cimpoi, "Deep filter banks for texture recognition and segmentation", ~
  16. L. Liu, "The Treasure beneath Convolutional Layers: Cross-convolutional-layer Pooling for Image Classification The Australian Centre for Robotic Vision", ~
  17. A. Babenko, "Aggregating Deep Convolutional Features for Image Retrieval", ~ (2015)
  18. Y. Kalantidis, "Crossdimensional Weighting for Aggregated Deep Convolutional Features", ~ (2015)
  19. G. Tolias, "Particular object retrieval with integral max-pooling of CNN activations", ~ (2015)
  20. Y. Gong, "Multiscale Orderless Pooling of Deep Convolutional Activation Features", ~ (2014)
  21. A. S. Razavian, "Visual Instance Retrieval with Deep Convolutional Networks", ~ (2014)
  22. H. Jégou, "Improving bagof-features for large scale image search", ~ (2009)
  23. A. Mikulik, "Learning Vocabularies over a Fine Quantization", Int. J. Comput. Vis, 103(1), pp.163~175 (2013)
  24. J. Philbin, "Object retrieval with large vocabularies and fast spatial matching", ~
  26. R. Tao, "Locality in Generic Instance Search from One Example", ~
  27. Y. Avrithis, "Hough Pyramid Matching:Speeded-Up Geometry Re-ranking for Large Scale Image Retrieval", Int. J. Comput. Vis, 107(1), pp.1~19 (2014)
  28. J. Philbin, "Lost in Quantization: Improving Particular Object Retrieval in Large Scale Image Databases", ~
  29. O. Chum, "Total Recall II: Query Expansion Revisited", ~
  30. G. Tolias, "Visual query expansion with or without geometry: refining local descriptors by feature aggregation" (2014)
  31. R. Arandjelovi, "Three things everyone should know to improve object retrieval", ~
  32. A. Mikulík, "Learning a Fine Vocabulary", ~
  33. H. Jegou, "Triangulation Embedding and Democratic Aggregation for Image Search", 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp.3310~3317 (2014)
  34. J. C. Wan, "Deep learning for content-based image retrieval:A comprehensive study Deep learning for contentbased image retrieval: A comprehensive study Deep Learning for Content-Based Image Retrieval: A Comprehensive Study", 157~166 (2014)
  35. C. Szegedy, "Going deeper with convolutions", Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit, 07–12, pp.1~9 (2015)
  36. H. Azizpour, "From Generic to Specific Deep Representations for Visual Recognition", ~
  37. G. Tolias, "PARTICULAR OBJECT RETRIEVAL WITH INTEGRAL MAX-POOLING OF CNN ACTIVATIONS", ~
  38. B. Zhou, "Learning Deep Features for Discriminative Localization", ~
  39. K. Simonyan, "Very deep convolutional networks for large-scale image recognition", Iclr, pp.1~14 (2015)
  40. O. Russakovsky, "ImageNet Large Scale Visual Recognition Challenge", Int. J. Comput. Vis, 115(3), pp.211~252 (2015)
  41. J. Xu, "Part-based Weighting Aggregation of Deep Convolutional Features for Image Retrieval", ~
  42. 김정혁, "가중치 초기화 컨벌루션 뉴럴 네트워크를 통한 대용량 이미지 도로 검출 및 태깅 시스템", 정보기술아키텍처 연구, 14(1), pp.67~72 (2017), 한국엔터프라이즈아키텍처학회
  43. 안길승, "신경망을 이용한 SNS상에서의 정보확산 예측모형: Digg 사례를 중심으로", 정보기술아키텍처 연구, 13(4), pp.609~616 (2016), 한국엔터프라이즈아키텍처학회
  44. Y. Jia, "Caffe: Convolutional Architecture for Fast Feature Embedding", Proc. ACM Int. Conf. Multimed, pp.675~678 (2014)

관련 논문AI추천

Convolutional Neural Network Based Multi-feature Fusion for Non-rigid 3D Model RetrievalHui Zeng, JianYong Che, Siqi Li, Xiuqing Wang, Yanrong Liu한국정보처리학회 · JIPS(Journal of Information Processing Systems)2018 · 제14권 제1호Learning-Based Multiple Pooling Fusion in Multi-View Convolutional Neural Network for 3D Model Classification and RetrievalChen Li, Hui Zeng, Qi Wang, Wei Song한국정보처리학회 · JIPS(Journal of Information Processing Systems)2019 · 제15권 제5호Analyzing Pedestrian Parts using Deep Features for Person Re-Identification울라 아민, 라힘 나시르, 백성욱, 이미영, 아마드 자밀한국차세대컴퓨팅학회 · 한국차세대컴퓨팅학회 논문지2017 · 제13권 제2호Combined Query Based Image Retrieval Using Structure Elements Descriptor정민중, Gunho Lee한국정보처리학회 · JIPS(Journal of Information Processing Systems)2025 · 제21권 제6호Content-Based Image Retrieval Using Multi-Resolution Multi-Direction Filtering-Based CLBP Texture Features and Color Autocorrelogram Features김남철, 김승호, 부희형, 윤병주한국정보처리학회 · JIPS(Journal of Information Processing Systems)2020 · 제16권 제4호Interactive Semantic Image RetrievalManesh Kokare, Pushpa B. Patil한국정보처리학회 · JIPS(Journal of Information Processing Systems)2013 · 제9권 제3호

이 간행물의 다른 논문 (6건)

Developing Big Data Usage Index Using AHP: Application of Major Industries홍필기, 김성현, 황현석pp. 211-219에너지-IT융합 기술 수용의도에 관한 연구박주석, 박재홍, 김이환pp. 231-249한국군 전술 에지 데이터 서비스(TEDS) 모델 - 지상 작전 중심으로 -임재성, 박범식pp. 251-264다단계 수송을 통한 물류합리화에 관한 연구 : 신선식품 위주로백종관, 김병찬pp. 265-275스마트폰 백신의 가치와 사용 의도에 영향을 미치는 요인에 관한 연구윤여준, 신동천pp. 277-287
원문 보기