Attention-based Dynamic Subspace Learners For Medical Image Analysis

Abstract

Learning similarity is a key aspect in medical image analysis, particularly in recommendation systems or in uncovering the interpretation of anatomical data in images. Most existing methods learn such similarities in the embedding space over image sets using a single metric learner. Images, however, have a variety of object attributes such as color, shape, or artifacts. Encoding such attributes using a single metric learner is inadequate and may fail to generalize. Instead, multiple learners could focus on separate aspects of these attributes in subspaces of an overarching embedding. This, however, implies the number of learners to be found empirically for each new dataset. This work, Dynamic Subspace Learners, proposes to dynamically exploit multiple learners by removing the need of knowing apriori the number of learners and aggregating new subspace learners during training. Furthermore, the visual interpretability of such subspace learning is enforced by integrating an attention modu

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyadiga2022attention

Related papers

• A New Similarity Space Tailored For Supervised Deep Metric Learning (2020)3.58
• Discriminative Supervised Subspace Learning For Cross-modal Retrieval (2022)0.00
• Attention-based Ensemble For Deep Metric Learning (2018)15.90
• Geometric Visual Similarity Learning In 3D Medical Image Self-supervised Pre-training (2023)16.30
• MRIS: A Multi-modal Retrieval Approach For Image Synthesis On Diverse Modalities (2023)3.58
• Visual Similarity Attention (2019)0.00
• Divide And Conquer The Embedding Space For Metric Learning (2019)14.39
• Dynamic Sampling For Deep Metric Learning (2020)5.84