Neighbor Embedding Projection and Rank-Based Manifold Learning for Image Retrieval

• Vinicius Atsushi Sato Kawai UNESP
• Gustavo Rosseto Leticio UNESP
• Lucas Pascotti Valem UNESP
• Daniel Carlos Guimarães Pedronette UNESP

Resumo

Despite the impressive advances in image under-standing approaches, defining similarity among images remains a challenging task, crucial for many applications such as classification and retrieval. Mainly supported by Convolution Neural Networks (CNNs) and Transformer-based models, image representation techniques are the main reason for the advances. On the other hand, comparisons are mostly computed based on traditional pairwise measures, such as the Euclidean distance, while contextual similarity approaches can lead to effective results in defining similarity between points in high-dimensional spaces. This paper introduces a novel approach to contextual similarity by combining two techniques: neighbor embedding projection methods and rank-based manifold learning. High-dimensional features are projected in a 2D space used for efficiently ranking computation. Subsequently, manifold learning methods are exploited for a re-ranking step. An experimental evaluation conducted on different datasets and visual features indicates that the proposed approach leads to significant gains in comparison to the original feature representations and the neighbor embedding method in isolation.

Palavras-chave: Visualization, Convolution, Image retrieval, Neural networks, Euclidean distance, Image representation, Transformers, Extraterrestrial measurements, Manifold learning, Convolutional neural networks