When Classes Evolve: A Benchmark and Framework for Stage-Aware Class-Incremental Learning

• URL: http://arxiv.org/abs/2602.00573v1
• Date: Sat, 31 Jan 2026 07:32:52 GMT
• Title: When Classes Evolve: A Benchmark and Framework for Stage-Aware Class-Incremental Learning
• Authors: Zheng Zhang, Tao Hu, Xueheng Li, Yang Wang, Rui Li, Jie Zhang, Chengjun Xie,
• Abstract summary: Class-Incremental Learning (CIL) aims to sequentially learn new classes while mitigating catastrophic forgetting of previously learned knowledge.<n>We propose Stage-Aware CIL, a paradigm in which each class is learned progressively through distinct morphological stages.<n>We also propose STAGE, a novel method that explicitly learns abstract and transferable evolution patterns within a fixed-size memory pool.
• Score: 17.13390892482038
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Class-Incremental Learning (CIL) aims to sequentially learn new classes while mitigating catastrophic forgetting of previously learned knowledge. Conventional CIL approaches implicitly assume that classes are morphologically static, focusing primarily on preserving previously learned representations as new classes are introduced. However, this assumption neglects intra-class evolution: a phenomenon wherein instances of the same semantic class undergo significant morphological transformations, such as a larva turning into a butterfly. Consequently, a model must both discriminate between classes and adapt to evolving appearances within a single class. To systematically address this challenge, we formalize Stage-Aware CIL (Stage-CIL), a paradigm in which each class is learned progressively through distinct morphological stages. To facilitate rigorous evaluation within this paradigm, we introduce the Stage-Bench, a 10-domain, 2-stages dataset and protocol that jointly measure inter- and intra-class forgetting. We further propose STAGE, a novel method that explicitly learns abstract and transferable evolution patterns within a fixed-size memory pool. By decoupling semantic identity from transformation dynamics, STAGE enables accurate prediction of future morphologies based on earlier representations. Extensive empirical evaluation demonstrates that STAGE consistently and substantially outperforms existing state-of-the-art approaches, highlighting its effectiveness in simultaneously addressing inter-class discrimination and intra-class morphological adaptation.

Related papers

• Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped Disentanglement [10.912635927529218]
  Class-Incremental Semantic (CISS) requires continuous learning of newly introduced classes while retaining knowledge of past classes.<n>This phenomenon involves Prototype-Feature Entanglement caused by semantic misalignment during the incremental process, and Background-Increment Entanglement due to dynamic data evolution.<n>We introduce a Language-inspired Bootstrapped Disentanglement framework (LBD)<n>We achieve state-of-the-art performance on both Pascal VOC and ADE20k, particularly in multi-step scenarios.
  arXiv  Detail & Related papers  (2025-08-30T15:18:58Z)
• Unified Generative and Discriminative Training for Multi-modal Large Language Models [88.84491005030316]
  Generative training has enabled Vision-Language Models (VLMs) to tackle various complex tasks. Discriminative training, exemplified by models like CLIP, excels in zero-shot image-text classification and retrieval. This paper proposes a unified approach that integrates the strengths of both paradigms.
  arXiv  Detail & Related papers  (2024-11-01T01:51:31Z)
• Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning [115.79349923044663]
  Few-shot class-incremental learning (FSCIL) aims to incrementally learn novel classes from limited examples.<n>Existing methods face a critical dilemma: static architectures rely on a fixed parameter space to learn from data that arrive sequentially, prone to overfitting to the current session.<n>In this study, we explore the potential of Selective State Space Models (SSMs) for FSCIL.
  arXiv  Detail & Related papers  (2024-07-08T17:09:39Z)
• Tendency-driven Mutual Exclusivity for Weakly Supervised Incremental Semantic Segmentation [56.1776710527814]
  Weakly Incremental Learning for Semantic (WILSS) leverages a pre-trained segmentation model to segment new classes using cost-effective and readily available image-level labels. A prevailing way to solve WILSS is the generation of seed areas for each new class, serving as a form of pixel-level supervision. We propose an innovative, tendency-driven relationship of mutual exclusivity, meticulously tailored to govern the behavior of the seed areas.
  arXiv  Detail & Related papers  (2024-04-18T08:23:24Z)
• Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration [67.69532794049445]
  We find a tendency for existing methods to misclassify the samples of new classes into base classes, which leads to the poor performance of new classes. We propose a simple yet effective Training-frEE calibratioN (TEEN) strategy to enhance the discriminability of new classes.
  arXiv  Detail & Related papers  (2023-12-08T18:24:08Z)
• Subclass-balancing Contrastive Learning for Long-tailed Recognition [38.31221755013738]
  Long-tailed recognition with imbalanced class distribution naturally emerges in practical machine learning applications. We propose a novel subclass-balancing contrastive learning'' approach that clusters each head class into multiple subclasses of similar sizes as the tail classes. We evaluate SBCL over a list of long-tailed benchmark datasets and it achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-06-28T05:08:43Z)
• Prototypical quadruplet for few-shot class incremental learning [24.814045065163135]
  We propose a novel method that improves classification robustness by identifying a better embedding space using an improved contrasting loss. Our approach retains previously acquired knowledge in the embedding space, even when trained with new classes. We demonstrate the effectiveness of our method by showing that the embedding space remains intact after training the model with new classes and outperforms existing state-of-the-art algorithms in terms of accuracy across different sessions.
  arXiv  Detail & Related papers  (2022-11-05T17:19:14Z)
• Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer [9.356870107137093]
  In class-incremental learning, the model is expected to learn new classes continually while maintaining knowledge on previous classes. We propose two distillation-based objectives for class incremental learning.
  arXiv  Detail & Related papers  (2022-08-07T16:28:02Z)
• DILF-EN framework for Class-Incremental Learning [9.969403314560179]
  We show that the effect of catastrophic forgetting on the model prediction varies with the change in orientation of the same image. We propose a novel data-ensemble approach that combines the predictions for the different orientations of the image. We also propose a novel dual-incremental learning framework that involves jointly training the network with two incremental learning objectives.
  arXiv  Detail & Related papers  (2021-12-23T06:49:24Z)
• Long-tail Recognition via Compositional Knowledge Transfer [60.03764547406601]
  We introduce a novel strategy for long-tail recognition that addresses the tail classes' few-shot problem. Our objective is to transfer knowledge acquired from information-rich common classes to semantically similar, and yet data-hungry, rare classes. Experiments show that our approach can achieve significant performance boosts on rare classes while maintaining robust common class performance.
  arXiv  Detail & Related papers  (2021-12-13T15:48:59Z)
• Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning [141.35105358670316]
  We study the difference between a na"ively-trained initial-phase model and the oracle model. We propose Class-wise Decorrelation (CwD) that effectively regularizes representations of each class to scatter more uniformly. Our CwD is simple to implement and easy to plug into existing methods.
  arXiv  Detail & Related papers  (2021-12-09T07:20:32Z)
• FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers [67.46036826589467]
  We present a novel regularization mechanism by learning the change of feature representations induced by a distribution of transformations without using the labels of data examples. It could minimize the risk of overfitting into base categories by inspecting the transformation-augmented variations at the encoded feature level. Experiment results show the superior performances to the current state-of-the-art methods in literature.
  arXiv  Detail & Related papers  (2019-12-29T15:26:28Z)

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.