# Hybrid Losses for Hierarchical Embedding Learning

arXiv: https://arxiv.org/abs/2501.12796 · HTML: https://mlsanity.com/paper/2501.12796/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 22 Jan 2025.

## Builds on (most cited first, 17 of 17)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Poincar'e Embeddings for Learning Hierarchical Representations](https://mlsanity.com/paper/1705.08039/) (2017)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [Sampling Matters in Deep Embedding Learning](https://mlsanity.com/paper/1706.07567/) (2017)
- [Hyperbolic Image Embeddings](https://mlsanity.com/paper/1904.02239/) (2019)
- [HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection](https://mlsanity.com/paper/2202.00874/) (2022)
- [Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks](https://mlsanity.com/paper/1912.09393/) (2019)
- [Smart Mining for Deep Metric Learning](https://mlsanity.com/paper/1704.01285/) (2017)
- [Embedding Label Structures for Fine-Grained Feature Representation](https://mlsanity.com/paper/1512.02895/) (2015)
- [Leveraging Hierarchical Structures for Few-Shot Musical Instrument Recognition](https://mlsanity.com/paper/2107.07029/) (2021)
- [SampleMatch: Drum Sample Retrieval by Musical Context](https://mlsanity.com/paper/2208.01141/) (2022)
- [Singer Identity Representation Learning using Self-Supervised Techniques](https://mlsanity.com/paper/2401.05064/) (2024)
- [OrchideaSOL: a dataset of extended instrumental techniques for computer-aided orchestration](https://mlsanity.com/paper/2007.00763/) (2020)
- [Rank-based loss for learning hierarchical representations](https://mlsanity.com/paper/2110.05941/) (2021)

## Built on by (most cited first, 1 of 1)

- [Hier-COS: Making Deep Features Hierarchy-aware via Composition of Orthogonal Subspaces](https://mlsanity.com/paper/2503.07853/) (2025)

## Abstract (arXiv)

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.