Hyperbolic Coarse-to-Fine Few-Shot Class-Incremental Learning

Jiaxin Dai, Xiang Xiang

TL;DR

This paper introduces HypKnowe, a framework that leverages hyperbolic geometry to improve how AI models learn specific sub-categories (fine classes) from very few examples after being trained on broad categories (coarse classes). By embedding data into a curved Poincaré ball rather than flat Euclidean space, the model better captures the natural hierarchy of information, leading to higher accuracy in few-shot incremental learning tasks.

What Problem Does This Paper Address?

The authors tackle the Coarse-to-Fine Few-Shot Class-Incremental Learning (C2FSCIL) problem. This task mimics how humans learn: we first recognize a broad category (e.g., "bird") and then, with just a few examples, learn to distinguish specific species (e.g., "sparrow" vs. "finch").

Standard machine learning models struggle here for three reasons:

  1. Catastrophic Forgetting: Learning new fine classes often causes the model to forget the coarse knowledge it already had.
  2. Data Scarcity: Learning from "few shots" (limited samples) usually leads to overfitting.
  3. Geometric Mismatch: Most models use Euclidean space, which is "flat." However, hierarchical data (like a taxonomy tree) grows exponentially. Hyperbolic space is naturally "curved" and provides much more "room" to represent these branching structures effectively.

Methods

The researchers built upon an existing algorithm called Knowe but moved the entire architecture into hyperbolic space using the Poincaré ball model. Their key technical contributions include:

  • Hyperbolic Mapping & FC Layers: They introduced a mapping layer that transforms standard Euclidean features into hyperbolic vectors. They also implemented Hyperbolic Fully-Connected (HypFC) layers to perform classification directly within the curved space.
  • Hyperbolic Contrastive Loss: Instead of using standard dot products to measure similarity, they used negative hyperbolic distances. This forces the model to cluster similar fine-grained features together while pushing different classes apart more effectively.
  • Distribution Estimation for Augmentation: To fight overfitting in few-shot scenarios, the model estimates the mean and variance of a class in hyperbolic space. It then uses a Wrapped Normal Distribution to sample "synthetic" features, effectively augmenting the training data without needing more real images.
  • Numerical Stability: The paper details a specific post-processing step to handle "round-off errors" that occur near the boundary of the Poincaré ball, preventing the model from crashing during training.

Datasets

The model was evaluated on three major benchmarks:

  • CIFAR-100: 20 coarse classes containing 5 fine classes each.
  • tieredImageNet: A larger subset of ImageNet with 20 coarse and 351 fine classes.
  • OpenEarthSensing (OES): A remote sensing dataset featuring 10 coarse categories (like "aviation") and 189 fine classes (specific aircraft models).

Key Insights and Ideas

  • Hierarchy is Hyperbolic: The "aha" moment is that the transition from coarse to fine labels is essentially a tree structure. Hyperbolic space is mathematically optimized for trees; as you move toward the edge of the Poincaré ball, the space expands exponentially, perfectly accommodating the increasing number of fine-grained sub-classes.
  • Freezing for Stability: By contrastively learning coarse features first and then "freezing" the feature extractor, the model prevents new fine-class data from corrupting the foundational knowledge.
  • The Power of Synthetic Features: Even in hyperbolic space, few-shot learning is hard. By generating augmented features from a calculated distribution, the model builds a more robust "mental map" of what a class looks like, even if it has only seen five real photos.

Key Results

The authors conducted ablation studies to prove that hyperbolic geometry was the primary driver of success:

  • Accuracy Boost: On CIFAR-100, the hyperbolic version achieved a fine-class accuracy of 46.4%, compared to 44.6% for the Euclidean baseline.
  • Remote Sensing Gains: On the OES dataset, the method improved fine-class accuracy by over 2.4% and significantly boosted the overall average accuracy across all learning sessions.
  • Forgetting Mitigation: Crucially, these gains didn't come at the cost of the "forgetting rate," which remained stable or improved, proving the model retained its initial coarse-level knowledge.

Limitations and Future Work

The authors acknowledge two main hurdles:

  1. Curvature Sensitivity: The performance of hyperbolic models is highly sensitive to the "curvature" parameter ($c$). Currently, this is set manually/empirically. Future work could involve learning the optimal curvature dynamically during training.
  2. Prototype Deviation: In extreme few-shot cases (e.g., only 1 or 2 images), the estimated distribution might be slightly off from the true distribution, leading to less effective data augmentation. The authors suggest that meta-learning strategies might be a way to refine these estimates in the future.

Summary updated

Abstract

In the field of machine learning, hyperbolic space demonstrates superior representation capabilities for hierarchical data compared to conventional Euclidean space. This work focuses on the Coarse-To-Fine Few-Shot Class-Incremental Learning (C2FSCIL) task. Our study follows the Knowe approach, which contrastively learns coarse class labels and subsequently normalizes and freezes the classifier weights of learned fine classes in the embedding space. To better interpret the "coarse-to-fine" paradigm, we propose embedding the feature extractor into hyperbolic space. Specifically, we employ the Poincaré ball model of hyperbolic space, enabling the feature extractor to transform input images into feature vectors within the Poincaré ball instead of Euclidean space. We further introduce hyperbolic contrastive loss and hyperbolic fully-connected layers to facilitate model optimization and classification in hyperbolic space. Additionally, to enhance performance under few-shot conditions, we implement maximum entropy distribution in hyperbolic space to estimate the probability distribution of fine-class feature vectors. This allows generation of augmented features from the distribution to mitigate overfitting during training with limited samples. Experiments on C2FSCIL benchmarks show that our method effectively improves both coarse and fine class accuracies.
BibTeX
@misc{dai2025hyperbolic,
  author = {Jiaxin Dai and Xiang Xiang},
  title = {{Hyperbolic Coarse-to-Fine Few-Shot Class-Incremental Learning}},
  year = {2025},
  eprint = {2509.18504},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.18504},
}
Figure