Hybrid Losses For Hierarchical Embedding Learning

Abstract

In traditional supervised learning, the cross-entropy loss treats all incorrect predictions equally, ignoring the relevance or proximity of wrong labels to the correct answer. By leveraging a tree hierarchy for fine-grained labels, we investigate hybrid losses, such as generalised triplet and cross-entropy losses, to enforce similarity between labels within a multi-task learning framework. We propose metrics to evaluate the embedding space structure and assess the model's ability to generalise to unseen classes, that is, to infer similar classes for data belonging to unseen categories. Our experiments on OrchideaSOL, a four-level hierarchical instrument sound dataset with nearly 200 detailed categories, demonstrate that the proposed hybrid losses outperform previous works in classification, retrieval, embedding space structure, and generalisation.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytian2025hybrid

Related papers

• Deep Metric Learning With Hierarchical Triplet Loss (2018)18.20
• A Quadruplet Loss For Enforcing Semantically Coherent Embeddings In Multi-output Classification Problems (2020)6.77
• Learning Visual Hierarchies In Hyperbolic Space For Image Retrieval (2024)0.00
• Hierarchical Proxy-based Loss For Deep Metric Learning (2021)10.85
• Hyp\(^2\) Loss: Beyond Hypersphere Metric Space For Multi-label Image Retrieval (2022)13.32
• Hierarchy Neighborhood Discriminative Hashing For An Unified View Of Single-label And Multi-label Image Retrieval (2019)0.00
• Constellation Loss: Improving The Efficiency Of Deep Metric Learning Loss Functions For Optimal Embedding (2019)0.00
• ARGENT: Adaptive Hierarchical Image-text Representations (2026)0.00