HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning

• URL: http://arxiv.org/abs/2604.15678v1
• Date: Fri, 17 Apr 2026 04:00:31 GMT
• Title: HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning
• Abstract summary: Few-Shot Class-Incremental Learning (FSCIL) methods assume homogeneous domains and balanced data distributions.<n>We identify Domain Gravity, a representational where data imbalance across heterogeneous domains causes overrepresented or low-entropy domains to disproportionately influence the embedding space.<n>We propose CrossDiscipline Variable Few-Shot Class-Incremental Learning (XD-VSCIL), a benchmark capturing real-world imbalance and asymmetry.<n>Experiments show HyCal effectively mitigates Domain Gravity and outperforms existing methods in imbalanced cross-domain incremental learning.
• Score: 21.424151495174033
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pretrained Vision-Language Models (VLMs) like CLIP show promise in continual learning, but existing Few-Shot Class-Incremental Learning (FSCIL) methods assume homogeneous domains and balanced data distributions, limiting real-world applicability where data arises from heterogeneous disciplines with imbalanced sample availability and varying visual complexity. We identify Domain Gravity, a representational asymmetry where data imbalance across heterogeneous domains causes overrepresented or low-entropy domains to disproportionately influence the embedding space, leading to prototype drift and degraded performance on underrepresented or high-entropy domains. To address this, we introduce Cross-Discipline Variable Few-Shot Class-Incremental Learning (XD-VSCIL), a benchmark capturing real-world heterogeneity and imbalance where Domain Gravity naturally intensifies. We propose Hybrid Prototype Calibration (HyCal), a training-free method combining cosine similarity and Mahalanobis distance to capture complementary geometric properties-directional alignment and covariance-aware magnitude-yielding stable prototypes under imbalanced heterogeneous conditions. Operating on frozen CLIP embeddings, HyCal achieves consistent retention-adaptation improvements while maintaining efficiency. Experiments show HyCal effectively mitigates Domain Gravity and outperforms existing methods in imbalanced cross-domain incremental learning.

Related papers

• Effective Covariance Dynamics in Solvable High-Dimensional GANs [2.639628765667673]
  We study a solvable high-dimensional model of generative adversarial network (GAN) training in which a linear generator learns a low-dimensional subspace from data.<n>We prove that the microscopic training process converges, in the high-dimensional limit, to deterministic ordinary differential equations governed by this effective covariance.
  arXiv  Detail & Related papers  (2026-06-25T16:33:54Z)
• Digital Twin-Driven Adaptive Sim-to-Real Alignment via Reinforcement Learning for Vibration-Based Bearing Health Monitoring Under Data Scarcity [7.28808693425028]
  vibration-based health monitoring of rotating machinery requires reliable fault diagnosis under operational data constraints.<n>We formulate feature alignment as a continuous-action Markov decision process solved via Proximal Policy Optimization.<n>An asymmetry-aware strategy reserves real data for the Normal class while augmenting fault classes with policy-aligned simulated samples.
  arXiv  Detail & Related papers  (2026-06-23T08:47:24Z)
• Hyperbolic Enhanced Representation Learning for Incomplete Multi-view Clustering [57.38215918201251]
  We propose HERL, a Hyperbolic Enhanced Representation Learning framework for Incomplete Multi-View Clustering.<n> operating within the Poincaré ball, HERL constructs a structure-aware latent space to enhance representation learning.<n>We show that HERL consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-04-18T10:50:46Z)
• Minimax optimal adaptive structured transfer learning through semi-parametric domain-varying coefficient model [9.091986429838117]
  We study a multi-source, single-target transfer learning problem under conditional distributional drift.<n>We develop an adaptive transfer learning estimator that selectively borrows strength from informative source domains.
  arXiv  Detail & Related papers  (2026-02-20T03:53:06Z)
• Modest-Align: Data-Efficient Alignment for Vision-Language Models [67.48633659305592]
  Cross-modal alignment models often suffer from overconfidence and degraded performance when operating in resource-constrained settings.<n>We propose Modest-Align, a lightweight alignment framework designed for robustness and efficiency.<n>Our method offers a practical and scalable solution for cross-modal alignment in real-world, low-resource scenarios.
  arXiv  Detail & Related papers  (2025-10-24T16:11:10Z)
• Harmonized Gradient Descent for Class Imbalanced Data Stream Online Learning [10.398611591652031]
  We introduce the harmonized gradient descent (HGD) algorithm, which aims to equalize the norms of gradients across different classes.<n>By ensuring the gradient norm balance, HGD mitigates under-fitting for minor classes and achieves balanced online learning.
  arXiv  Detail & Related papers  (2025-08-15T09:35:13Z)
• Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation [27.5393760658806]
  Unsupervised Graph Domain Adaptation (UGDA) leverages labeled source domain graphs to achieve effective performance in unlabeled target domains despite distribution shifts.<n>We propose SLOGAN, a novel approach that achieves stable graph representation transfer through sparse causal modeling and dynamic intervention mechanisms.
  arXiv  Detail & Related papers  (2025-07-10T10:42:21Z)
• Unbiased Max-Min Embedding Classification for Transductive Few-Shot Learning: Clustering and Classification Are All You Need [83.10178754323955]
  Few-shot learning enables models to generalize from only a few labeled examples.<n>We propose the Unbiased Max-Min Embedding Classification (UMMEC) Method, which addresses the key challenges in few-shot learning.<n>Our method significantly improves classification performance with minimal labeled data, advancing the state-of-the-art in annotatedL.
  arXiv  Detail & Related papers  (2025-03-28T07:23:07Z)
• Adaptive Federated Learning Over the Air [108.62635460744109]
  We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. Our analysis shows that the AdaGrad-based training algorithm converges to a stationary point at the rate of $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• Gradient Reweighting: Towards Imbalanced Class-Incremental Learning [8.438092346233054]
  Class-Incremental Learning (CIL) trains a model to continually recognize new classes from non-stationary data. A major challenge of CIL arises when applying to real-world data characterized by non-uniform distribution. We show that this dual imbalance issue causes skewed gradient updates with biased weights in FC layers, thus inducing over/under-fitting and catastrophic forgetting in CIL.
  arXiv  Detail & Related papers  (2024-02-28T18:08:03Z)
• Combating Representation Learning Disparity with Geometric Harmonization [50.29859682439571]
  We propose a novel Geometric Harmonization (GH) method to encourage category-level uniformity in representation learning. Our proposal does not alter the setting of SSL and can be easily integrated into existing methods in a low-cost manner.
  arXiv  Detail & Related papers  (2023-10-26T17:41:11Z)
• Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment [130.84010267004803]
  Training a generative adversarial network (GAN) with limited data has been a challenging task. A feasible solution is to start with a GAN well-trained on a large scale source domain and adapt it to the target domain with a few samples, termed as few shot generative model adaption. We propose a relaxed spatial structural alignment method to calibrate the target generative models during the adaption.
  arXiv  Detail & Related papers  (2022-03-06T14:26:25Z)
• Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning [126.31716228319902]
  We develop Distribution Aligning Refinery of Pseudo-label (DARP) algorithm. We show that DARP is provably and efficiently compatible with state-of-the-art SSL schemes.
  arXiv  Detail & Related papers  (2020-07-17T09:16:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.