Image Similarity Using An Ensemble Of Context-sensitive Models

Abstract

Image similarity has been extensively studied in computer vision. In recent years, machine-learned models have shown their ability to encode more semantics than traditional multivariate metrics. However, in labelling semantic similarity, assigning a numerical score to a pair of images is impractical, making the improvement and comparisons on the task difficult. In this work, we present a more intuitive approach to build and compare image similarity models based on labelled data in the form of A:R vs B:R, i.e., determining if an image A is closer to a reference image R than another image B. We address the challenges of sparse sampling in the image space (R, A, B) and biases in the models trained with context-based data by using an ensemble model. Our testing results show that the ensemble model constructed performs ~5% better than the best individual context-sensitive models. They also performed better than the models that were directly fine-tuned using mixed imagery data as well as exi

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyliao2024image

Related papers

• Evaluating Contrastive Models For Instance-based Image Retrieval (2021)5.24
• Contextual Visual Similarity (2016)0.00
• Context Sensitivity Improves Human-machine Visual Alignment (2026)0.00
• Supervised Metric Learning To Rank For Retrieval Via Contextual Similarity Optimization (2022)2.64
• Learning Similarity Conditions Without Explicit Supervision (2019)13.93
• Genecis: A Benchmark For General Conditional Image Similarity (2023)10.07
• Learning To Embed Semantic Similarity For Joint Image-text Retrieval (2022)7.50
• Combination Of Multiple Global Descriptors For Image Retrieval (2019)0.00