Automated Siamese Network Design for Image Similarity Computation - Archive ouverte HAL
Communication Dans Un Congrès Année : 2023

Automated Siamese Network Design for Image Similarity Computation

Résumé

Despite the success of Siamese networks in image indexing, face recognition, and signature verification, there has been little research on designing their architectural space compared to convolutional neural networks (CNNs). This work aims to automate the design process of Siamese network architectures and improve their performance in tasks that involve image similarity computing such as indexing and retrieval. To achieve this goal, in contrast with the current literature that focuses on improving the design of the backbone CNN, we use Differentiable Neural Architecture Search (DNAS) to explore the architecture of the Multi-Layer Perceptron (MLP) component of siamese networks, namely the projector and/or predictor heads. The main objective of these MLPs is to enhance the ability of backbone CNNs to learn strong representations from unlabeled data. Using a well-known contrastive learning framework (SimCLR) as a baseline, we show that our approach managed to improve performance on several computer vision tasks such as image classification (ImageNet) and content-based image retrieval (INRIA Holidays).
Fichier non déposé

Dates et versions

hal-04420941 , version 1 (27-01-2024)

Identifiants

Citer

Alexandre Heuillet, Hedi Tabia, Hichem Arioui. Automated Siamese Network Design for Image Similarity Computation. 20th International Conference on Content-based Multimedia Indexing (CBMI 2023), Sep 2023, Orleans, France. pp.8--13, ⟨10.1145/3617233.3617243⟩. ⟨hal-04420941⟩
50 Consultations
0 Téléchargements

Altmetric

Partager

More