효율적인 이미지 검색 시스템을 위한자기 감독 딥해싱 모델의 비교 분석
Comparative Analysis of Self-supervised Deephashing Models for Efficient Image Retrieval System
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
해싱 기반 이미지 검색에서는 조작된 이미지의 해시코드가 원본 이미지와 달라 동일한 이미지 검색이 어렵다. 본 논문은 이미지의 질감, 모양,색상 등 특징 정보로부터 지각적 해시코드를 생성하는 자기 감독 기반 딥해싱 모델을 제안하고 평가한다. 비교 모델은 오토인코더 기반 변분 추론모델들이며, 인코더는 완전 연결 계층, 합성곱 신경망과 트랜스포머 모듈 등으로 설계된다. 제안된 모델은 기하학적 패턴을 추출하고 이미지 내위치 관계를 활용하는 SimAM 모듈을 포함하는 변형 추론 모델이다. SimAM은 뉴런과 주변 뉴런의 활성화 값을 이용한 에너지 함수를 통해 객체또는 로컬 영역이 강조된 잠재 벡터를 학습할 수 있다. 제안 방법은 표현 학습 모델로 고차원 입력 이미지의 저차원 잠재 벡터를 생성할 수 있으며,잠재 벡터는 구분 가능한 해시코드로 이진화 된다. CIFAR-10, ImageNet, NUS-WIDE 등 공개 데이터셋의 실험 결과로부터 제안 모델은 비교모델보다 우수하며, 지도학습 기반 딥해싱 모델과 동등한 성능이 분석되었다.
Abstract
In hashing-based image retrieval, the hash code of a manipulated image is different from the original image, making it difficult tosearch for the same image. This paper proposes and evaluates a self-supervised deephashing model that generates perceptual hash codesfrom feature information such as texture, shape, and color of images. The comparison models are autoencoder-based variational inferencemodels, but the encoder is designed with a fully connected layer, convolutional neural network, and transformer modules. The proposedmodel is a variational inference model that includes a SimAM module of extracting geometric patterns and positional relationships withinimages. The SimAM module can learn latent vectors highlighting objects or local regions through an energy function using the activationvalues of neurons and surrounding neurons. The proposed method is a representation learning model that can generate low-dimensionallatent vectors from high-dimensional input images, and the latent vectors are binarized into distinguishable hash code. From theexperimental results on public datasets such as CIFAR-10, ImageNet, and NUS-WIDE, the proposed model is superior to the comparativemodel and analyzed to have equivalent performance to the supervised learning-based deephashing model. The proposed model can beused in application systems that require low-dimensional representation of images, such as image search or copyright image determination.
참고문헌 (18)
- L. Du, "Perceptual hashing for image authentication : A survey", Signal Processing : Image Communication, 81, pp.115713~ (2020)
- J. Mao, "An image authentication technology based on depth residual network", Systems Science & Control Engineering, 6(1), pp.57~70 (2018)
- D. Kim, "A photo identification framework to prevent copyright infringement with manipulations", Applied Sciences, 11(19), pp.9194~ (2021)
- S. Zhu, "A new image encryption algorithm based on chaos and secure hash sha-256", Entropy, 20(9), pp.716~ (2018)
- L. W. Kang, "Compressive sensingbased image hashing", 2009 16th IEEE International Conference on Image Processing (ICIP). IEEE, pp.1285~1288 (2009)
- K. P. Murphy, "Probabilistic Machine Learning : An introduction" (2022), MIT Press
- G. E Hinton, "Transforming auto-encoders", Artificial Neural Networks and Machine Learning–ICANN 2011: 21st International Conference on Artificial Neural Networks, pp.44~51 (2011), Springer
- D. P. Kingma, "Auto-encoding variational bayes", 2nd International Conference on Learning Representations, ICLR 2014 (2014)
- X. Chen, "Evolving deep convolutional variational autoencoders for image classification", IEEE Transactions on Evolutionary Computation, 25(5), pp.815~829 (2020)
- A. Dosovitskiy, "An image is worth 16x16 words : Transformers for image recognition at scale", arXiv preprint arXiv:2010.11929, ~ (2020)
- L. Yang, "Simam: A simple, parameter-free attention module for convolutional neural networks", Proceedings of the 38th International Conference on Machine Learning, 139, pp.11863~11874 (2021), PMLR
- H. Venkateswara, "Deep hashing network for unsupervised domain adaptation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.5018~5027 (2017)
- A. Krizhevsky, "Imagenet classification with deep convolutional neural networks", Advances in Neural Information Processing Systems, 25 (2012)
- K. Simonyan, "Very deep convolutional networks for large-scale image recognition", arXiv preprint arXiv:1409.1556, ~ (2014)
- V. Gattupalli, "Weakly supervised deep image hashing through tag embeddings", Proceedings of the IEEE, 2019, 10375~10384
- H. Liu, "Deep supervised hashing for fast image retrieval", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
- Z. Cao, "Hashnet : Deep learning to hash by continuation", Proceedings of the IEEE International Conference on Computer Vision (2017)
- S. R. Dubey, "Vision transformer hashing for image retrieval", 2022 IEEE International Conference on Multimedia and Expo (ICME). IEEE (2022)